{
  "schema_version": 1,
  "source_commit": "a231aacfde338efdf041724053d3b320f0ffc33d",
  "benchmark_scores_sha256": "baa9a1af5f18484be42a920194a1c6e940f2f91bbf86fb8c2721588886758aaa",
  "policy": {
    "normalization": "1 / (1 + J / task_scale)",
    "design": "Best eligible evaluated design",
    "implementation": "Eligible final submission",
    "invalid": "Raw score is null; zero contributes to distributions and comparisons",
    "missing": "Not attempted/published; excluded, never zero",
    "comparison": "Only tasks with an attempted result for both selected systems",
    "distribution": "Fraction of attempted tasks with aggregate score >= threshold; no resolution criterion"
  },
  "default_pair": {
    "x": "claude-code:openrouter/anthropic/claude-opus-5.5",
    "y": "codex:openrouter/openai/gpt-6-astra"
  },
  "models": [
    {
      "key": "codex:openrouter/openai/gpt-5.6-sol",
      "agent": "codex",
      "model": "gpt-5.6-sol",
      "reasoning_effort": "medium",
      "label": "GPT-5.6 Sol - Codex",
      "color": "#589ee4",
      "marker": "o"
    },
    {
      "key": "codex:openrouter/openai/gpt-6.1-sol",
      "agent": "codex",
      "model": "gpt-6.1-sol",
      "reasoning_effort": "medium",
      "label": "GPT-6.1 Sol - Codex",
      "color": "#227ad3",
      "marker": "s"
    },
    {
      "key": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "agent": "claude-code",
      "model": "claude-opus-5.5",
      "reasoning_effort": "medium",
      "label": "Opus 5.5 - Claude Code",
      "color": "#c35f18",
      "marker": "^"
    },
    {
      "key": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "agent": "claude-code",
      "model": "claude-fable-5.1",
      "reasoning_effort": "medium",
      "label": "Fable 5.1 - Claude Code",
      "color": "#e98c49",
      "marker": "D"
    },
    {
      "key": "codex:openrouter/openai/gpt-6-astra",
      "agent": "codex",
      "model": "gpt-6-astra",
      "reasoning_effort": "medium",
      "label": "GPT-6 Astra - Codex",
      "color": "#185795",
      "marker": "P"
    },
    {
      "key": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "agent": "mini-swe-agent",
      "model": "glm-5.3-flash",
      "reasoning_effort": "max",
      "label": "GLM 5.3 Flash (max) - mini-SWE-agent",
      "color": "#217d57",
      "marker": "v"
    },
    {
      "key": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "agent": "mini-swe-agent",
      "model": "gemini-4-argon",
      "reasoning_effort": "medium",
      "label": "Gemini 4 Argon - mini-SWE-agent",
      "color": "#7a33c1",
      "marker": "X"
    },
    {
      "key": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "agent": "claude-code",
      "model": "glm-5.3-flash",
      "reasoning_effort": "high",
      "label": "GLM 5.3 Flash (high) - Claude Code",
      "color": "#2ca573",
      "marker": "p"
    },
    {
      "key": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "agent": "claude-code",
      "model": "kimi-k3.1-pro",
      "reasoning_effort": "medium",
      "label": "Kimi K3.1 Pro - Claude Code",
      "color": "#c4316e",
      "marker": "h"
    },
    {
      "key": "muse-code:openrouter/meta/muse-wonder",
      "agent": "muse-code",
      "model": "muse-wonder",
      "reasoning_effort": "high",
      "label": "Muse Wonder (high) - Muse Code",
      "color": "#1fa6b2",
      "marker": "<"
    },
    {
      "key": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "agent": "claude-code",
      "model": "claude-sonnet-5.5",
      "reasoning_effort": "high",
      "label": "Sonnet 5.5 (high) - Claude Code",
      "color": "#da6a1b",
      "marker": ">"
    }
  ],
  "tasks": [
    {
      "id": "90sinwaveguide-design-v0",
      "title": "90 Degree SiN Waveguide Bend Design",
      "label": "SiN bend",
      "kind": "design",
      "href": "/tasks/90sinwaveguide-design-v0"
    },
    {
      "id": "eight-delay-mzi-spectrometer-design-v1",
      "title": "Compact PDK-Physical Eight-Delay Sparse-Spectrum MZI Spectrometer",
      "label": "MZI-Spec-8",
      "kind": "design",
      "href": "/tasks/eight-delay-mzi-spectrometer-design-v1"
    },
    {
      "id": "four-mode-quantum-projector-electrothermal-design-v1",
      "title": "Four-Mode Quantum Projector Electrothermal Design",
      "label": "Quantum-4",
      "kind": "design",
      "href": "/tasks/four-mode-quantum-projector-electrothermal-design-v1"
    },
    {
      "id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "title": "Eight-Mode Quantum Projector Electrothermal Design",
      "label": "Quantum-8",
      "kind": "design",
      "href": "/tasks/eight-mode-quantum-projector-electrothermal-design-v2"
    },
    {
      "id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "title": "Four-Wavelength Two-Port Ring Selective Cross-Connect",
      "label": "Ring-XC-v1",
      "kind": "design",
      "href": "/tasks/four-wavelength-two-port-selective-crossconnect-design-v1"
    },
    {
      "id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "title": "Four-Wavelength Four-Port Ring Selective Cross-Connect",
      "label": "Ring-XC-v2",
      "kind": "design",
      "href": "/tasks/four-wavelength-four-port-selective-crossconnect-design-v2"
    },
    {
      "id": "microresonator-modulator-design-v1",
      "title": "Single-Ring O-Band Microresonator Modulator",
      "label": "MRM-v1",
      "kind": "design",
      "href": "/tasks/microresonator-modulator-design-v1"
    },
    {
      "id": "microresonator-modulator-design-v2",
      "title": "Five-Channel C-Band WDM-PAM4 Microresonator Modulator",
      "label": "MRM-v2",
      "kind": "design",
      "href": "/tasks/microresonator-modulator-design-v2"
    },
    {
      "id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "title": "Microring-Assisted Fourier Spectrometer Electrothermal Design",
      "label": "RAFT-Spec",
      "kind": "design",
      "href": "/tasks/microring-assisted-fourier-spectrometer-electrothermal-design-v1"
    },
    {
      "id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "title": "MZI-Coupled Microring Add-Drop Filter Electrothermal Design",
      "label": "MZI-Ring-v1",
      "kind": "design",
      "href": "/tasks/mzi-coupled-microring-add-drop-filter-electrothermal-design-v1"
    },
    {
      "id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "title": "MZI-coupled microring add-drop filter electrothermal design v2",
      "label": "MZI-Ring-v2",
      "kind": "design",
      "href": "/tasks/mzi-coupled-microring-add-drop-filter-electrothermal-design-v2"
    },
    {
      "id": "rectangular-mzi-mesh-design-v1",
      "title": "Broadband 4x4 Rectangular MZI Mesh",
      "label": "MZI-v1",
      "kind": "design",
      "href": "/tasks/rectangular-mzi-mesh-design-v1"
    },
    {
      "id": "rectangular-mzi-mesh-design-v2",
      "title": "Broadband 6x6 Rectangular MZI Mesh",
      "label": "MZI-v2",
      "kind": "design",
      "href": "/tasks/rectangular-mzi-mesh-design-v2"
    },
    {
      "id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "title": "Serial Dual-Ring-Assisted MZI Elliptic Bandpass Electrothermal Design v1",
      "label": "Serial MZI-v1",
      "kind": "design",
      "href": "/tasks/serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1"
    },
    {
      "id": "wdm-channelizer-electrothermal-design-v1",
      "title": "Four-Channel Electrothermal Dual-Ring WDM Channelizer",
      "label": "WDM-v1",
      "kind": "design",
      "href": "/tasks/wdm-channelizer-electrothermal-design-v1"
    },
    {
      "id": "wdm-channelizer-electrothermal-design-v2",
      "title": "Eight-Channel Electrothermal Dual-Ring WDM Channelizer",
      "label": "WDM-v2",
      "kind": "design",
      "href": "/tasks/wdm-channelizer-electrothermal-design-v2"
    },
    {
      "id": "anisotropic-swg-beamsplitter-v0",
      "title": "Anisotropic SWG 2 x 2 Beamsplitter Implementation/Optimization",
      "label": "Anisotropic SWG",
      "kind": "implementation",
      "href": "/tasks/anisotropic-swg-beamsplitter-v0"
    },
    {
      "id": "asi-sin-swg-grating-coupler-v0",
      "title": "\u03b1-Si/Si3N4 SWG Grating Coupler Implementation/Optimization",
      "label": "\u03b1-Si/SiN grating",
      "kind": "implementation",
      "href": "/tasks/asi-sin-swg-grating-coupler-v0"
    },
    {
      "id": "dual-trident-swg-edge-coupler-v0",
      "title": "Dual-Trident SWG Edge Coupler Implementation/Optimization",
      "label": "Dual-trident",
      "kind": "implementation",
      "href": "/tasks/dual-trident-swg-edge-coupler-v0"
    },
    {
      "id": "hmdm-polarization-splitter-rotator-v1",
      "title": "HMDM Polarization Splitter\u2013Rotator Implementation/Optimization",
      "label": "HMDM PSR",
      "kind": "implementation",
      "href": "/tasks/hmdm-polarization-splitter-rotator-v1"
    },
    {
      "id": "hmdm-six-channel-wdm-v1",
      "title": "HMDM Six-Channel WDM Binary Optimization",
      "label": "HMDM WDM",
      "kind": "implementation",
      "href": "/tasks/hmdm-six-channel-wdm-v1"
    },
    {
      "id": "sb2se3-si-polarization-rotator-v0",
      "title": "Sb2Se3/Si Reconfigurable Polarization Rotator Implementation/Optimization",
      "label": "Sb\u2082Se\u2083 rotator",
      "kind": "implementation",
      "href": "/tasks/sb2se3-si-polarization-rotator-v0"
    },
    {
      "id": "srsn-grating-coupler-v0",
      "title": "SRSN Grating Coupler Implementation/Optimization",
      "label": "SRSN grating",
      "kind": "implementation",
      "href": "/tasks/srsn-grating-coupler-v0"
    },
    {
      "id": "tfln-mmi-crossing-v0",
      "title": "Three-Direction TFLN MMI Crossing Implementation/Optimization",
      "label": "TFLN crossing",
      "kind": "implementation",
      "href": "/tasks/tfln-mmi-crossing-v0"
    },
    {
      "id": "tfln-polarization-insensitive-mmi-v0",
      "title": "Polarization-Insensitive TFLN 1x2 MMI Implementation/Optimization",
      "label": "TFLN PI-MMI",
      "kind": "implementation",
      "href": "/tasks/tfln-polarization-insensitive-mmi-v0"
    },
    {
      "id": "trapezoidal-swg-3db-coupler-v0",
      "title": "Trapezoidal SWG 2 x 2 3-dB Coupler Implementation/Optimization",
      "label": "Trapezoidal SWG",
      "kind": "implementation",
      "href": "/tasks/trapezoidal-swg-3db-coupler-v0"
    }
  ],
  "cells": [
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.6361800396941798,
      "aggregate_score": 0.6361800396941798,
      "run_id": "gpt-5.6-sol-medium__x9CirZ3"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.6534307984139784,
      "aggregate_score": 0.6534307984139784,
      "run_id": "gpt-6.1-sol-medium__epDbWm4"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.7387238915066675,
      "aggregate_score": 0.7387238915066675,
      "run_id": "claude-opus-5.5-medium__ufmS4nF"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.7606122563609441,
      "aggregate_score": 0.7606122563609441,
      "run_id": "claude-fable-5.1-medium__X4585ui"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.7187399937056109,
      "aggregate_score": 0.7187399937056109,
      "run_id": "gpt-6-astra-medium__6x6EBm3"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.6207050424078983,
      "aggregate_score": 0.6207050424078983,
      "run_id": "mini-swe-glm-5.3-flash-max__dYyD8hL"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.7021156787592263,
      "aggregate_score": 0.7021156787592263,
      "run_id": "mini-swe-gemini-4-argon-medium__ND7EmLV"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.517664216696222,
      "aggregate_score": 0.517664216696222,
      "run_id": "claude-glm-5.3-flash-high__CgsijUb"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.6426622734286004,
      "aggregate_score": 0.6426622734286004,
      "run_id": "claude-kimi-3.1-pro-medium__ZbK7MoM"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.6735879303212895,
      "aggregate_score": 0.6735879303212895,
      "run_id": "muse-code-muse-wonder-high__2MSuUix"
    },
    {
      "task_id": "90sinwaveguide-design-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.6087565404049666,
      "aggregate_score": 0.6087565404049666,
      "run_id": "claude-sonnet-5.5-high__SunCSSu"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.33878091155868706,
      "aggregate_score": 0.33878091155868706,
      "run_id": "gpt-5.6-sol-medium__JkeyJR5"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.49800749617660317,
      "aggregate_score": 0.49800749617660317,
      "run_id": "gpt-6.1-sol-medium__ijpbVWD"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.48324977453300166,
      "aggregate_score": 0.48324977453300166,
      "run_id": "claude-opus-5.5-medium__VWFkx2G"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.4937987098938226,
      "aggregate_score": 0.4937987098938226,
      "run_id": "claude-fable-5.1-medium__7mifcZd"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.5075629709329448,
      "aggregate_score": 0.5075629709329448,
      "run_id": "gpt-6-astra-medium__LMj3dzw"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.483885752872493,
      "aggregate_score": 0.483885752872493,
      "run_id": "mini-swe-glm-5.3-flash-max__JeirxPQ"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.503603182574645,
      "aggregate_score": 0.503603182574645,
      "run_id": "mini-swe-gemini-4-argon-medium__NP9heXn"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.45381826123284746,
      "aggregate_score": 0.45381826123284746,
      "run_id": "claude-glm-5.3-flash-high__yVdAuVy"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.47302824397604043,
      "aggregate_score": 0.47302824397604043,
      "run_id": "claude-kimi-3.1-pro-medium__W3Jd2Pv"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.480042612482891,
      "aggregate_score": 0.480042612482891,
      "run_id": "muse-code-muse-wonder-high__CALm5qC"
    },
    {
      "task_id": "eight-delay-mzi-spectrometer-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.4686436623424256,
      "aggregate_score": 0.4686436623424256,
      "run_id": "claude-sonnet-5.5-high__iXG3Nfd"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.2142640140115024,
      "aggregate_score": 0.2142640140115024,
      "run_id": "gpt-5.6-sol-medium__ZbL9w7m"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.5766862186486919,
      "aggregate_score": 0.5766862186486919,
      "run_id": "gpt-6.1-sol-medium__652EteU"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.49306781364962693,
      "aggregate_score": 0.49306781364962693,
      "run_id": "claude-opus-5.5-medium__hXCo6Fy"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.4966583303002153,
      "aggregate_score": 0.4966583303002153,
      "run_id": "claude-fable-5.1-medium__4MMNDZ6"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.570023769243036,
      "aggregate_score": 0.570023769243036,
      "run_id": "gpt-6-astra-medium__vBxekmf"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__NQqfv2P"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.5057486418861779,
      "aggregate_score": 0.5057486418861779,
      "run_id": "mini-swe-gemini-4-argon-medium__zd8az6V"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__FkCwFeX"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.287471000933517,
      "aggregate_score": 0.287471000933517,
      "run_id": "claude-kimi-3.1-pro-medium__y9aCxZy"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.457816969439274,
      "aggregate_score": 0.457816969439274,
      "run_id": "muse-code-muse-wonder-high__o5KDsiV"
    },
    {
      "task_id": "four-mode-quantum-projector-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.518054561522018,
      "aggregate_score": 0.518054561522018,
      "run_id": "claude-sonnet-5.5-high__qEduR59"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.12220497163388283,
      "aggregate_score": 0.12220497163388283,
      "run_id": "gpt-5.6-sol-medium__LrSFzei"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.3448586873633828,
      "aggregate_score": 0.3448586873633828,
      "run_id": "gpt-6.1-sol-medium__F86X2NV"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.37968825335478157,
      "aggregate_score": 0.37968825335478157,
      "run_id": "claude-opus-5.5-medium__UYHaLet"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.09755683516728182,
      "aggregate_score": 0.09755683516728182,
      "run_id": "claude-fable-5.1-medium__ULMLy4J"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.47871136652350327,
      "aggregate_score": 0.47871136652350327,
      "run_id": "gpt-6-astra-medium__7F2nbWm"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__oAZYnoq"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__y5suwF9"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__5kJoMFY"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__CZybt5c"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__2RsXKHi"
    },
    {
      "task_id": "eight-mode-quantum-projector-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-sonnet-5.5-high__R2rRa9v"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-5.6-sol-medium__wUFL6c2"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-6.1-sol-medium__P3eosxx"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.37340977145473225,
      "aggregate_score": 0.37340977145473225,
      "run_id": "claude-opus-5.5-medium__5zNjE7T"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-fable-5.1-medium__ueM5wHw"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.3110633262371042,
      "aggregate_score": 0.3110633262371042,
      "run_id": "gpt-6-astra-medium__ZxtsHVd"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__ju6sYbM"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__yfLas3L"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__fcHmkUj"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.3741286095773444,
      "aggregate_score": 0.3741286095773444,
      "run_id": "claude-kimi-3.1-pro-medium__RhEZSTu"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__UqbdQMW"
    },
    {
      "task_id": "four-wavelength-two-port-selective-crossconnect-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-sonnet-5.5-high__EnLiWnE"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-5.6-sol-medium__DggULv4"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-6.1-sol-medium__agM724R"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-opus-5.5-medium__wX6g3KS"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-fable-5.1-medium__vmHiNCU"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.4332451860711778,
      "aggregate_score": 0.4332451860711778,
      "run_id": "gpt-6-astra-medium__2sEePwQ"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__Fw3FV2g"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__hXpqvYx"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__BcDGXGJ"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__ttAxvcH"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__Wwb2eza"
    },
    {
      "task_id": "four-wavelength-four-port-selective-crossconnect-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-sonnet-5.5-high__MCjW4St"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.62475728832264,
      "aggregate_score": 0.62475728832264,
      "run_id": "gpt-5.6-sol-medium__koZvscB"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.7761290005300021,
      "aggregate_score": 0.7761290005300021,
      "run_id": "gpt-6.1-sol-medium__WizSc8M"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.7798511040040472,
      "aggregate_score": 0.7798511040040472,
      "run_id": "claude-opus-5.5-medium__bYQxY9j"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.6302856963516489,
      "aggregate_score": 0.6302856963516489,
      "run_id": "claude-fable-5.1-medium__tnLHS3s"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.7520321846928425,
      "aggregate_score": 0.7520321846928425,
      "run_id": "gpt-6-astra-medium__zvzQ7Gr"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.46141767615403056,
      "aggregate_score": 0.46141767615403056,
      "run_id": "mini-swe-glm-5.3-flash-max__Ekg79AR"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__8ANoWB5"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__EiZU2bf"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.6142964651993187,
      "aggregate_score": 0.6142964651993187,
      "run_id": "claude-kimi-3.1-pro-medium__YHRYx2z"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.49103449995180887,
      "aggregate_score": 0.49103449995180887,
      "run_id": "muse-code-muse-wonder-high__9EwsfgU"
    },
    {
      "task_id": "microresonator-modulator-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.6500767513442852,
      "aggregate_score": 0.6500767513442852,
      "run_id": "claude-sonnet-5.5-high__qciKn75"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-5.6-sol-medium__iMCNtyv"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.6016832263944605,
      "aggregate_score": 0.6016832263944605,
      "run_id": "gpt-6.1-sol-medium__WyxUbj7"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.5301374794082211,
      "aggregate_score": 0.5301374794082211,
      "run_id": "claude-opus-5.5-medium__pgZw2z7"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.5664501788803392,
      "aggregate_score": 0.5664501788803392,
      "run_id": "claude-fable-5.1-medium__cyDpbSb"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.5934528563636889,
      "aggregate_score": 0.5934528563636889,
      "run_id": "gpt-6-astra-medium__Bwukre6"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__QJPtDoN"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.59337838071237,
      "aggregate_score": 0.59337838071237,
      "run_id": "mini-swe-gemini-4-argon-medium__KSfCNe7"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__UzbxNde"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__TxMqx32"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__nJQbH9e"
    },
    {
      "task_id": "microresonator-modulator-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.513596240119381,
      "aggregate_score": 0.513596240119381,
      "run_id": "claude-sonnet-5.5-high__mmc6JLa"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.42179026450559803,
      "aggregate_score": 0.42179026450559803,
      "run_id": "gpt-5.6-sol-medium__L6hjS6U"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.44259132386991806,
      "aggregate_score": 0.44259132386991806,
      "run_id": "gpt-6.1-sol-medium__zmmjfU2"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.4339633522541484,
      "aggregate_score": 0.4339633522541484,
      "run_id": "claude-opus-5.5-medium__TV7PiR3"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.4232513813804586,
      "aggregate_score": 0.4232513813804586,
      "run_id": "claude-fable-5.1-medium__JnF4ks7"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.4423954306698299,
      "aggregate_score": 0.4423954306698299,
      "run_id": "gpt-6-astra-medium__aVCtQZr"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__cPVQxXJ"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.4394578612196238,
      "aggregate_score": 0.4394578612196238,
      "run_id": "mini-swe-gemini-4-argon-medium__sSByStd"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__FoEnePZ"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.40899026811114425,
      "aggregate_score": 0.40899026811114425,
      "run_id": "claude-kimi-3.1-pro-medium__R9jaLNW"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__kAYvfxs"
    },
    {
      "task_id": "microring-assisted-fourier-spectrometer-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.4124165581887242,
      "aggregate_score": 0.4124165581887242,
      "run_id": "claude-sonnet-5.5-high__XMGsTQ6"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.2702876087411493,
      "aggregate_score": 0.2702876087411493,
      "run_id": "gpt-5.6-sol-medium__b65fYhK"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.28399419894118916,
      "aggregate_score": 0.28399419894118916,
      "run_id": "gpt-6.1-sol-medium__ZVrtQRc"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.3773556507606345,
      "aggregate_score": 0.3773556507606345,
      "run_id": "claude-opus-5.5-medium__PKhzDDf"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.23865138718253884,
      "aggregate_score": 0.23865138718253884,
      "run_id": "claude-fable-5.1-medium__5wtZyDJ"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.40442875610862644,
      "aggregate_score": 0.40442875610862644,
      "run_id": "gpt-6-astra-medium__viHZoff"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__eEiuSoe"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.4143822578984347,
      "aggregate_score": 0.4143822578984347,
      "run_id": "mini-swe-gemini-4-argon-medium__N3nJUkV"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__b6oHuqa"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.04273125232748044,
      "aggregate_score": 0.04273125232748044,
      "run_id": "claude-kimi-3.1-pro-medium__WGU2Rjx"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__6yu7298"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.3528205677891258,
      "aggregate_score": 0.3528205677891258,
      "run_id": "claude-sonnet-5.5-high__yJbeCEz"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-5.6-sol-medium__pQsgVqS"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.008839316556922654,
      "aggregate_score": 0.008839316556922654,
      "run_id": "gpt-6.1-sol-medium__aCkc3sW"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.010313740815086639,
      "aggregate_score": 0.010313740815086639,
      "run_id": "claude-opus-5.5-medium__AxiRRkZ"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.01008221812445078,
      "aggregate_score": 0.01008221812445078,
      "run_id": "claude-fable-5.1-medium__QHGxcKe"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.01613903912128535,
      "aggregate_score": 0.01613903912128535,
      "run_id": "gpt-6-astra-medium__ADJzqzq"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__ZfCrMkj"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__SdEVK5u"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__Zm79Ysm"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__LYh9xmC"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.006750835310177694,
      "aggregate_score": 0.006750835310177694,
      "run_id": "muse-code-muse-wonder-high__KrTsyaY"
    },
    {
      "task_id": "mzi-coupled-microring-add-drop-filter-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-sonnet-5.5-high__TE6cMEh"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.32564516041544783,
      "aggregate_score": 0.32564516041544783,
      "run_id": "gpt-5.6-sol-medium__rm2F3dF"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.7217026366796359,
      "aggregate_score": 0.7217026366796359,
      "run_id": "gpt-6.1-sol-medium__qY2QpwW"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.6713053539812365,
      "aggregate_score": 0.6713053539812365,
      "run_id": "claude-opus-5.5-medium__DnnS7DX"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.32091266342880415,
      "aggregate_score": 0.32091266342880415,
      "run_id": "claude-fable-5.1-medium__p6L67SA"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.5407385198491005,
      "aggregate_score": 0.5407385198491005,
      "run_id": "gpt-6-astra-medium__HxjZXGk"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__CBL7RuW"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__gUDG9BK"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__jvA5Krr"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__DQAEqVo"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__cFSG4tF"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.6830454959396963,
      "aggregate_score": 0.6830454959396963,
      "run_id": "claude-sonnet-5.5-high__u3ZUTxW"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-5.6-sol-medium__CMU5JWT"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.4117472423736596,
      "aggregate_score": 0.4117472423736596,
      "run_id": "gpt-6.1-sol-medium__BGPHN7w"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.41203226405981686,
      "aggregate_score": 0.41203226405981686,
      "run_id": "claude-opus-5.5-medium__uz5k2WH"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.5317228558330231,
      "aggregate_score": 0.5317228558330231,
      "run_id": "claude-fable-5.1-medium__ogxq7JE"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.7858743752447025,
      "aggregate_score": 0.7858743752447025,
      "run_id": "gpt-6-astra-medium__tE3o6Z7"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__Yp4obs2"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__8f6Wb2J"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__USU4WSX"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__hpza6wv"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__dwrHMLJ"
    },
    {
      "task_id": "rectangular-mzi-mesh-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.3876858617114657,
      "aggregate_score": 0.3876858617114657,
      "run_id": "claude-sonnet-5.5-high__HDFxUFR"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "gpt-5.6-sol-medium__oQNYkQY"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.10153721394449455,
      "aggregate_score": 0.10153721394449455,
      "run_id": "gpt-6.1-sol-medium__MFT49ZJ"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.03904816237237949,
      "aggregate_score": 0.03904816237237949,
      "run_id": "claude-opus-5.5-medium__gqZ5BGk"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.04052154822218704,
      "aggregate_score": 0.04052154822218704,
      "run_id": "claude-fable-5.1-medium__NNqZ7rS"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.047267971591325925,
      "aggregate_score": 0.047267971591325925,
      "run_id": "gpt-6-astra-medium__zbB8JRY"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__3L9Vxuz"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.3042577689020623,
      "aggregate_score": 0.3042577689020623,
      "run_id": "mini-swe-gemini-4-argon-medium__b4ZjpFu"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__gUsBMCX"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.09861799773180026,
      "aggregate_score": 0.09861799773180026,
      "run_id": "claude-kimi-3.1-pro-medium__j2nvbJ9"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.038239563544342346,
      "aggregate_score": 0.038239563544342346,
      "run_id": "muse-code-muse-wonder-high__PqPuKVA"
    },
    {
      "task_id": "serial-dual-ring-assisted-mzi-chebyshev-elliptic-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-sonnet-5.5-high__Rz6fEKC"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.09588675211905683,
      "aggregate_score": 0.09588675211905683,
      "run_id": "gpt-5.6-sol-medium__Bae7Ds5"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.8114654217844703,
      "aggregate_score": 0.8114654217844703,
      "run_id": "gpt-6.1-sol-medium__YDxETJr"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.5019281027808474,
      "aggregate_score": 0.5019281027808474,
      "run_id": "claude-opus-5.5-medium__H5nespn"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.6060222988820587,
      "aggregate_score": 0.6060222988820587,
      "run_id": "claude-fable-5.1-medium__Q2Hwos2"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.8460337409387738,
      "aggregate_score": 0.8460337409387738,
      "run_id": "gpt-6-astra-medium__hxEcUh2"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__pLuTH94"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__HX4MLN3"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__wKiYbav"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__VPA2FGw"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.6029023943919835,
      "aggregate_score": 0.6029023943919835,
      "run_id": "muse-code-muse-wonder-high__nV8AMxi"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.13258408122689672,
      "aggregate_score": 0.13258408122689672,
      "run_id": "claude-sonnet-5.5-high__9sJ6tsA"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.06562767497950764,
      "aggregate_score": 0.06562767497950764,
      "run_id": "gpt-5.6-sol-medium__h8dxhLJ"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.0559597539059596,
      "aggregate_score": 0.0559597539059596,
      "run_id": "gpt-6.1-sol-medium__pXQy5gb"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.688899593926791,
      "aggregate_score": 0.688899593926791,
      "run_id": "claude-opus-5.5-medium__wJgtV7n"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-fable-5.1-medium__RyZsvm4"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.7140598341785158,
      "aggregate_score": 0.7140598341785158,
      "run_id": "gpt-6-astra-medium__bKasNsW"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-glm-5.3-flash-max__fjqXQG6"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "mini-swe-gemini-4-argon-medium__DQULSPD"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-glm-5.3-flash-high__h55gdhP"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "claude-kimi-3.1-pro-medium__Hah5bnw"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "invalid",
      "score": null,
      "aggregate_score": 0,
      "run_id": "muse-code-muse-wonder-high__MyLVaER"
    },
    {
      "task_id": "wdm-channelizer-electrothermal-design-v2",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.3555753870658507,
      "aggregate_score": 0.3555753870658507,
      "run_id": "claude-sonnet-5.5-high__PMEYGtq"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.6387661578437166,
      "aggregate_score": 0.6387661578437166,
      "run_id": "gpt-5.6-sol-medium__oqGPswA"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.639989381729571,
      "aggregate_score": 0.639989381729571,
      "run_id": "gpt-6.1-sol-medium__abPZVfb"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.6334707071939112,
      "aggregate_score": 0.6334707071939112,
      "run_id": "claude-opus-5.5-medium__p9AUZWB"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.3894556984521428,
      "aggregate_score": 0.3894556984521428,
      "run_id": "claude-fable-5.1-medium__7JWetKL"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.6774711234801927,
      "aggregate_score": 0.6774711234801927,
      "run_id": "gpt-6-astra-medium__JgUnFEB"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.3121822542926429,
      "aggregate_score": 0.3121822542926429,
      "run_id": "mini-swe-glm-5.3-flash-max__chMi3Xu"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.7051176704391768,
      "aggregate_score": 0.7051176704391768,
      "run_id": "mini-swe-gemini-4-argon-medium__V8rhTzV"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.31725062551007926,
      "aggregate_score": 0.31725062551007926,
      "run_id": "claude-glm-5.3-flash-high__LQ8dMhT"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.3660489148256816,
      "aggregate_score": 0.3660489148256816,
      "run_id": "claude-kimi-3.1-pro-medium__ttKPyPR"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.6687679096929441,
      "aggregate_score": 0.6687679096929441,
      "run_id": "muse-code-muse-wonder-high__mht2SW4"
    },
    {
      "task_id": "anisotropic-swg-beamsplitter-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.5989949008226845,
      "aggregate_score": 0.5989949008226845,
      "run_id": "claude-sonnet-5.5-high__gWp88bQ"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.21644088699204606,
      "aggregate_score": 0.21644088699204606,
      "run_id": "gpt-5.6-sol-medium__fneTGyW"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.2619879635428269,
      "aggregate_score": 0.2619879635428269,
      "run_id": "gpt-6.1-sol-medium__xti6PUE"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.26147278979954097,
      "aggregate_score": 0.26147278979954097,
      "run_id": "claude-opus-5.5-medium__ZgMn83m"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.2721807222527886,
      "aggregate_score": 0.2721807222527886,
      "run_id": "claude-fable-5.1-medium__ZUAvAqH"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.26562794965722686,
      "aggregate_score": 0.26562794965722686,
      "run_id": "gpt-6-astra-medium__o5mkyGV"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.2191894471971506,
      "aggregate_score": 0.2191894471971506,
      "run_id": "mini-swe-glm-5.3-flash-max__tnikS2q"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.2167134322443861,
      "aggregate_score": 0.2167134322443861,
      "run_id": "mini-swe-gemini-4-argon-medium__DeQmq2W"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.21237667645945302,
      "aggregate_score": 0.21237667645945302,
      "run_id": "claude-glm-5.3-flash-high__5sQX8gx"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.21076113426160803,
      "aggregate_score": 0.21076113426160803,
      "run_id": "claude-kimi-3.1-pro-medium__Arq7FXg"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.22801641185296104,
      "aggregate_score": 0.22801641185296104,
      "run_id": "muse-code-muse-wonder-high__djCj4mt"
    },
    {
      "task_id": "asi-sin-swg-grating-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.2660925457727225,
      "aggregate_score": 0.2660925457727225,
      "run_id": "claude-sonnet-5.5-high__2ND8PQS"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.14025473324122587,
      "aggregate_score": 0.14025473324122587,
      "run_id": "gpt-5.6-sol-medium__Tefaf2b"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.35291020178663096,
      "aggregate_score": 0.35291020178663096,
      "run_id": "gpt-6.1-sol-medium__kmPU9c6"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.3660993671300349,
      "aggregate_score": 0.3660993671300349,
      "run_id": "claude-opus-5.5-medium__zH36ssc"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.35891801707646,
      "aggregate_score": 0.35891801707646,
      "run_id": "claude-fable-5.1-medium__rQWz8vT"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.34635766536518414,
      "aggregate_score": 0.34635766536518414,
      "run_id": "gpt-6-astra-medium__ehhq8bJ"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.1793938136325614,
      "aggregate_score": 0.1793938136325614,
      "run_id": "mini-swe-glm-5.3-flash-max__NzLprDu"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.3483604985813429,
      "aggregate_score": 0.3483604985813429,
      "run_id": "mini-swe-gemini-4-argon-medium__kjGw67N"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.10873437123054448,
      "aggregate_score": 0.10873437123054448,
      "run_id": "claude-glm-5.3-flash-high__nk5f6SG"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.31793633341638283,
      "aggregate_score": 0.31793633341638283,
      "run_id": "claude-kimi-3.1-pro-medium__ovCPKjQ"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.2775492747288133,
      "aggregate_score": 0.2775492747288133,
      "run_id": "muse-code-muse-wonder-high__kc4dJx7"
    },
    {
      "task_id": "dual-trident-swg-edge-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.34503427647435514,
      "aggregate_score": 0.34503427647435514,
      "run_id": "claude-sonnet-5.5-high__u6shDGb"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.09834109344942302,
      "aggregate_score": 0.09834109344942302,
      "run_id": "gpt-5.6-sol-medium__fusBtYp"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.11828049146978163,
      "aggregate_score": 0.11828049146978163,
      "run_id": "gpt-6.1-sol-medium__2zL4MbS"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.0941998043272081,
      "aggregate_score": 0.0941998043272081,
      "run_id": "claude-opus-5.5-medium__4eq4a8k"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.09194864160399174,
      "aggregate_score": 0.09194864160399174,
      "run_id": "claude-fable-5.1-medium__4hUvnmJ"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.10770237140578208,
      "aggregate_score": 0.10770237140578208,
      "run_id": "gpt-6-astra-medium__dg6GzEg"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.09064978822800958,
      "aggregate_score": 0.09064978822800958,
      "run_id": "mini-swe-glm-5.3-flash-max__rDSoXbz"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.09064978822800958,
      "aggregate_score": 0.09064978822800958,
      "run_id": "mini-swe-gemini-4-argon-medium__fPDGrbz"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.09347494797119142,
      "aggregate_score": 0.09347494797119142,
      "run_id": "claude-glm-5.3-flash-high__P2ozu8L"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.0935145751916076,
      "aggregate_score": 0.0935145751916076,
      "run_id": "claude-kimi-3.1-pro-medium__JonhPxy"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.0922959928062678,
      "aggregate_score": 0.0922959928062678,
      "run_id": "muse-code-muse-wonder-high__jzHnxFb"
    },
    {
      "task_id": "hmdm-polarization-splitter-rotator-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.10414193147419563,
      "aggregate_score": 0.10414193147419563,
      "run_id": "claude-sonnet-5.5-high__XHkzDN8"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.06293380415175254,
      "aggregate_score": 0.06293380415175254,
      "run_id": "gpt-5.6-sol-medium__yTrWHVA"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.30880526772642947,
      "aggregate_score": 0.30880526772642947,
      "run_id": "gpt-6.1-sol-medium__5beMqGZ"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.0499615013167435,
      "aggregate_score": 0.0499615013167435,
      "run_id": "claude-opus-5.5-medium__dDuit3o"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.2520281567152502,
      "aggregate_score": 0.2520281567152502,
      "run_id": "claude-fable-5.1-medium__icW2tNW"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.31043385662829176,
      "aggregate_score": 0.31043385662829176,
      "run_id": "gpt-6-astra-medium__UTpkRSg"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.30624914397208475,
      "aggregate_score": 0.30624914397208475,
      "run_id": "mini-swe-glm-5.3-flash-max__ZAeg2yb"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.2402573656967712,
      "aggregate_score": 0.2402573656967712,
      "run_id": "mini-swe-gemini-4-argon-medium__SKKchLi"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.2135007774410379,
      "aggregate_score": 0.2135007774410379,
      "run_id": "claude-glm-5.3-flash-high__w2k7PZF"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.15310894215491386,
      "aggregate_score": 0.15310894215491386,
      "run_id": "claude-kimi-3.1-pro-medium__FT6EJ8u"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.24765993513165993,
      "aggregate_score": 0.24765993513165993,
      "run_id": "muse-code-muse-wonder-high__XP9Snvg"
    },
    {
      "task_id": "hmdm-six-channel-wdm-v1",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.027895012123852297,
      "aggregate_score": 0.027895012123852297,
      "run_id": "claude-sonnet-5.5-high__3o3b4nZ"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.4952368019829872,
      "aggregate_score": 0.4952368019829872,
      "run_id": "gpt-5.6-sol-medium__AHe49nL"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.6494821029958469,
      "aggregate_score": 0.6494821029958469,
      "run_id": "gpt-6.1-sol-medium__bppadf9"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.7332612211072795,
      "aggregate_score": 0.7332612211072795,
      "run_id": "claude-opus-5.5-medium__HF57FEr"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.49680649150668704,
      "aggregate_score": 0.49680649150668704,
      "run_id": "claude-fable-5.1-medium__BXQPtnX"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.9332491232383588,
      "aggregate_score": 0.9332491232383588,
      "run_id": "gpt-6-astra-medium__jxAVwNt"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.14512154263122745,
      "aggregate_score": 0.14512154263122745,
      "run_id": "mini-swe-glm-5.3-flash-max__WKb8Gxp"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.26454961708752234,
      "aggregate_score": 0.26454961708752234,
      "run_id": "mini-swe-gemini-4-argon-medium__8puYjxn"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.2645439707647997,
      "aggregate_score": 0.2645439707647997,
      "run_id": "claude-glm-5.3-flash-high__bCGnWkM"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.49895577150117576,
      "aggregate_score": 0.49895577150117576,
      "run_id": "claude-kimi-3.1-pro-medium__LvNswLU"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.5185045540402909,
      "aggregate_score": 0.5185045540402909,
      "run_id": "muse-code-muse-wonder-high__wJq3K7w"
    },
    {
      "task_id": "sb2se3-si-polarization-rotator-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.46600673626893496,
      "aggregate_score": 0.46600673626893496,
      "run_id": "claude-sonnet-5.5-high__BzycvYy"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.5234189600943097,
      "aggregate_score": 0.5234189600943097,
      "run_id": "gpt-5.6-sol-medium__aQX2HEz"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.5735620830508639,
      "aggregate_score": 0.5735620830508639,
      "run_id": "gpt-6.1-sol-medium__ysHtDKq"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.5245230115009233,
      "aggregate_score": 0.5245230115009233,
      "run_id": "claude-opus-5.5-medium__pU9s9SJ"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.5555296266041198,
      "aggregate_score": 0.5555296266041198,
      "run_id": "claude-fable-5.1-medium__Xrqjuj9"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.5910548436098062,
      "aggregate_score": 0.5910548436098062,
      "run_id": "gpt-6-astra-medium__vCvAHHL"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.5223148576352938,
      "aggregate_score": 0.5223148576352938,
      "run_id": "mini-swe-glm-5.3-flash-max__QMWnvm2"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.5188912791079026,
      "aggregate_score": 0.5188912791079026,
      "run_id": "mini-swe-gemini-4-argon-medium__vnXsJAR"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.5200164289965413,
      "aggregate_score": 0.5200164289965413,
      "run_id": "claude-glm-5.3-flash-high__oWTJTMW"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.5228030864507712,
      "aggregate_score": 0.5228030864507712,
      "run_id": "claude-kimi-3.1-pro-medium__vvyLKDN"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.5322993752873164,
      "aggregate_score": 0.5322993752873164,
      "run_id": "muse-code-muse-wonder-high__MYj3Myt"
    },
    {
      "task_id": "srsn-grating-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.5252678166446767,
      "aggregate_score": 0.5252678166446767,
      "run_id": "claude-sonnet-5.5-high__VP86VRz"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.20095334936841802,
      "aggregate_score": 0.20095334936841802,
      "run_id": "gpt-5.6-sol-medium__GSf8dS7"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.2939934914747829,
      "aggregate_score": 0.2939934914747829,
      "run_id": "gpt-6.1-sol-medium__9sPumXa"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.1692134160239034,
      "aggregate_score": 0.1692134160239034,
      "run_id": "claude-opus-5.5-medium__btZUm9A"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.3639702751614457,
      "aggregate_score": 0.3639702751614457,
      "run_id": "claude-fable-5.1-medium__EBWBnUS"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.21966146946106893,
      "aggregate_score": 0.21966146946106893,
      "run_id": "gpt-6-astra-medium__F6ixc8B"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.12377821846668703,
      "aggregate_score": 0.12377821846668703,
      "run_id": "mini-swe-glm-5.3-flash-max__qxD6ndg"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.19270294587155884,
      "aggregate_score": 0.19270294587155884,
      "run_id": "mini-swe-gemini-4-argon-medium__JuRx42Z"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.2707734806426086,
      "aggregate_score": 0.2707734806426086,
      "run_id": "claude-glm-5.3-flash-high__xxKphsf"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.14555032627199016,
      "aggregate_score": 0.14555032627199016,
      "run_id": "claude-kimi-3.1-pro-medium__PpEgttR"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.2916886533463981,
      "aggregate_score": 0.2916886533463981,
      "run_id": "muse-code-muse-wonder-high__qmgzNk2"
    },
    {
      "task_id": "tfln-mmi-crossing-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.29664417205258137,
      "aggregate_score": 0.29664417205258137,
      "run_id": "claude-sonnet-5.5-high__Uw3WhX4"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.3049339286623199,
      "aggregate_score": 0.3049339286623199,
      "run_id": "gpt-5.6-sol-medium__F3oW8VQ"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.3210074433962336,
      "aggregate_score": 0.3210074433962336,
      "run_id": "gpt-6.1-sol-medium__aJ8eCHH"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.3268281333290578,
      "aggregate_score": 0.3268281333290578,
      "run_id": "claude-opus-5.5-medium__inD5Ts5"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.33507775087621566,
      "aggregate_score": 0.33507775087621566,
      "run_id": "claude-fable-5.1-medium__tegB3CK"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.3260467662640333,
      "aggregate_score": 0.3260467662640333,
      "run_id": "gpt-6-astra-medium__YcWLFhC"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.11951566732022427,
      "aggregate_score": 0.11951566732022427,
      "run_id": "mini-swe-glm-5.3-flash-max__ECexJyy"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.22418078271491182,
      "aggregate_score": 0.22418078271491182,
      "run_id": "mini-swe-gemini-4-argon-medium__5iDK9br"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.25197770801028024,
      "aggregate_score": 0.25197770801028024,
      "run_id": "claude-glm-5.3-flash-high__6L7SYwT"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.2725072820282175,
      "aggregate_score": 0.2725072820282175,
      "run_id": "claude-kimi-3.1-pro-medium__Lifn5PW"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.3051738020476209,
      "aggregate_score": 0.3051738020476209,
      "run_id": "muse-code-muse-wonder-high__JtVCUCU"
    },
    {
      "task_id": "tfln-polarization-insensitive-mmi-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.3051811892463718,
      "aggregate_score": 0.3051811892463718,
      "run_id": "claude-sonnet-5.5-high__qJczomm"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "codex:openrouter/openai/gpt-5.6-sol",
      "status": "valid",
      "score": 0.26403929369988727,
      "aggregate_score": 0.26403929369988727,
      "run_id": "gpt-5.6-sol-medium__kGkPeq9"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6.1-sol",
      "status": "valid",
      "score": 0.4658781905649029,
      "aggregate_score": 0.4658781905649029,
      "run_id": "gpt-6.1-sol-medium__jwMZJGw"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-opus-5.5",
      "status": "valid",
      "score": 0.30612062716957517,
      "aggregate_score": 0.30612062716957517,
      "run_id": "claude-opus-5.5-medium__rTfxRuH"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-fable-5.1",
      "status": "valid",
      "score": 0.36439523107946303,
      "aggregate_score": 0.36439523107946303,
      "run_id": "claude-fable-5.1-medium__dF3sy7U"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "codex:openrouter/openai/gpt-6-astra",
      "status": "valid",
      "score": 0.39734267737485385,
      "aggregate_score": 0.39734267737485385,
      "run_id": "gpt-6-astra-medium__WbiQvhn"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "mini-swe-agent:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.33758133628679343,
      "aggregate_score": 0.33758133628679343,
      "run_id": "mini-swe-glm-5.3-flash-max__EpmfWeB"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "mini-swe-agent:openrouter/google/gemini-4-argon",
      "status": "valid",
      "score": 0.28216008656421165,
      "aggregate_score": 0.28216008656421165,
      "run_id": "mini-swe-gemini-4-argon-medium__HV573Dh"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "claude-code:openrouter/z-ai/glm-5.3-flash",
      "status": "valid",
      "score": 0.035006850225307445,
      "aggregate_score": 0.035006850225307445,
      "run_id": "claude-glm-5.3-flash-high__FG9dqqy"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "claude-code:openrouter/moonshotai/kimi-k3.1-pro",
      "status": "valid",
      "score": 0.2540998379095957,
      "aggregate_score": 0.2540998379095957,
      "run_id": "claude-kimi-3.1-pro-medium__9ByhuAU"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "muse-code:openrouter/meta/muse-wonder",
      "status": "valid",
      "score": 0.37138043874940374,
      "aggregate_score": 0.37138043874940374,
      "run_id": "muse-code-muse-wonder-high__AxCGcp2"
    },
    {
      "task_id": "trapezoidal-swg-3db-coupler-v0",
      "series": "claude-code:openrouter/anthropic/claude-sonnet-5.5",
      "status": "valid",
      "score": 0.3486541591974601,
      "aggregate_score": 0.3486541591974601,
      "run_id": "claude-sonnet-5.5-high__pDLwURU"
    }
  ]
}
