PhysDesignBench
GitHub
Design task · v2

Microresonator-v2

Five-Channel C-Band WDM-PAM4 Microresonator Modulator

Design a five-channel C-band WDM-PAM4 microresonator modulator array with two-segment junctions, independent heaters, and trusted optical, RF, electrical, and thermal verification.

Runs
13
Scored finals
8 of 13
Best final
S = 0.60 GPT-6.1 Sol · Codex
Score over timeBest-so-far score S for each run · small dots are probes, large dots final submissions
Score S from 0 to 1 against elapsed minutes. Final scores: GPT-6.1 Sol (Codex) 0.602; GPT-6 Astra (Codex) 0.593; Gemini 4 Argon (mini-SWE-agent) 0.593; GPT-6.1 Sol (mini-SWE-agent) 0.582; Fable 5.1 (Claude Code) 0.566; Sonnet 5.5 (mini-SWE-agent) 0.534; Opus 5.5 (Claude Code) 0.530; Sonnet 5.5 (high) (Claude Code) 0.514; GLM 5.3 Flash (high) (Claude Code) Invalid; GLM 5.3 Flash (max) (mini-SWE-agent) Invalid; GPT-5.6 Sol (Codex) Invalid; Kimi K3.1 Pro (Claude Code) Invalid; Muse Wonder (high) (Muse Code) Invalid.0.000.250.500.751.000153045607590105120135Elapsed time (min)Score SSonnet 5.5 · mini-SWE-agent: final S = 0.534 at 108 minGPT-6.1 Sol · mini-SWE-agent: final S = 0.582 at 121 minGLM 5.3 Flash (high) · Claude Code: final Invalid at 121 minGLM 5.3 Flash (max) · mini-SWE-agent: final Invalid at 60 minGPT-5.6 Sol · Codex: final Invalid at 121 minKimi K3.1 Pro · Claude Code: final Invalid at 122 minMuse Wonder (high) · Muse Code: final Invalid at 117 minSonnet 5.5 (high) · Claude Code: final S = 0.514 at 122 minOpus 5.5 · Claude Code: final S = 0.530 at 114 minFable 5.1 · Claude Code: final S = 0.566 at 95 minGemini 4 Argon · mini-SWE-agent: final S = 0.593 at 121 minGPT-6 Astra · Codex: final S = 0.593 at 121 minGPT-6.1 Sol · Codex: final S = 0.602 at 122 min

Showing 13 of 13 runs. Hover a line or a model to isolate it; click a model to hide or show it.

Final layouts

Every run’s final GDS, at one scale.

The design each run ended with, drawn from its evaluated GDS. Every layout uses the same physical scale, so sizes compare directly. Hatched layouts failed a validity gate and score zero. Select a layout to zoom and toggle its layers.

  • Optical mask
  • Si ring
  • Active slab
  • P implant
  • N implant
  • P+ implant
  • N+ implant
  • Contact via
  • Heater
  • Metal
  • Pad opening

  • Microresonator-v2 · Codex · GPT-6.1-sol

    S = 0.602 · scale bar 200 µm

    Fit
    GPT-6.1 SolCodexS = 0.60

  • Microresonator-v2 · Codex · GPT-6 Astra

    S = 0.593 · scale bar 200 µm

    Fit
    GPT-6 AstraCodexS = 0.59

  • Microresonator-v2 · mini-SWE-agent · Gemini-4-Argon

    S = 0.593 · scale bar 200 µm

    Fit
    Gemini 4 Argonmini-SWE-agentS = 0.59

  • Microresonator-v2 · mini-SWE-agent · GPT-6.1-sol

    S = 0.582 · scale bar 200 µm

    Fit
    GPT-6.1 Solmini-SWE-agentS = 0.58

  • Microresonator-v2 · Claude Code · Claude Fable 5.1

    S = 0.566 · scale bar 200 µm

    Fit
    Fable 5.1Claude CodeS = 0.57

  • Microresonator-v2 · mini-SWE-agent · Claude Sonnet 5.5

    S = 0.534 · scale bar 200 µm

    Fit
    Sonnet 5.5mini-SWE-agentS = 0.53

  • Microresonator-v2 · Claude Code · Claude Opus 5.5

    S = 0.530 · scale bar 200 µm

    Fit
    Opus 5.5Claude CodeS = 0.53

  • Microresonator-v2 · Claude Code · Claude Sonnet 5.5

    S = 0.514 · scale bar 200 µm

    Fit
    Sonnet 5.5 (high)Claude CodeS = 0.51

  • Microresonator-v2 · Claude Code · GLM 5.3 Flash

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    GLM 5.3 Flash (high)Claude CodeInvalid · S = 0

  • Microresonator-v2 · mini-SWE-agent · GLM 5.3 Flash

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    GLM 5.3 Flash (max)mini-SWE-agentInvalid · S = 0

  • Microresonator-v2 · Codex · GPT-5.6-sol

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    GPT-5.6 SolCodexInvalid · S = 0

  • Microresonator-v2 · Claude Code · Kimi K3.1 Pro

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    Kimi K3.1 ProClaude CodeInvalid · S = 0

  • Microresonator-v2 · Muse Code · Muse Wonder

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    Muse Wonder (high)Muse CodeInvalid · S = 0