PhysDesignBench
GitHub
Design task · v2

WDM-v2

Eight-Channel Electrothermal Dual-Ring WDM Channelizer

Design an eight-channel dual-ring WDM channelizer near 1310 nm with 16 independently heated rings and trusted electrothermal scoring.

Runs
13
Scored finals
5 of 13
Best final
S = 0.71 GPT-6 Astra · 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 Astra (Codex) 0.711; Opus 5.5 (Claude Code) 0.683; Sonnet 5.5 (high) (Claude Code) 0.340; GPT-5.6 Sol (Codex) 0.066; GPT-6.1 Sol (Codex) 0.056; Fable 5.1 (Claude Code) Invalid; Gemini 4 Argon (mini-SWE-agent) Invalid; GLM 5.3 Flash (high) (Claude Code) Invalid; GLM 5.3 Flash (max) (mini-SWE-agent) Invalid; GPT-6.1 Sol (mini-SWE-agent) Invalid; Kimi K3.1 Pro (Claude Code) Invalid; Muse Wonder (high) (Muse Code) Invalid; Sonnet 5.5 (mini-SWE-agent) Invalid.0.000.250.500.751.000153045607590105120135150Elapsed time (min)Score SGPT-6.1 Sol · mini-SWE-agent: final Invalid at 140 minSonnet 5.5 · mini-SWE-agent: final Invalid at 137 minFable 5.1 · Claude Code: final Invalid at 140 minGemini 4 Argon · mini-SWE-agent: final Invalid at 138 minGLM 5.3 Flash (high) · Claude Code: final Invalid at 114 minGLM 5.3 Flash (max) · mini-SWE-agent: final Invalid at 56 minKimi K3.1 Pro · Claude Code: final Invalid at 121 minMuse Wonder (high) · Muse Code: final Invalid at 140 minGPT-6.1 Sol · Codex: final S = 0.056 at 146 minGPT-5.6 Sol · Codex: final S = 0.066 at 140 minSonnet 5.5 (high) · Claude Code: final S = 0.340 at 131 minOpus 5.5 · Claude Code: final S = 0.683 at 137 minGPT-6 Astra · Codex: final S = 0.711 at 131 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
  • Heater
  • Metal
  • Pad opening

  • WDM-v2 · Codex · GPT-6 Astra

    S = 0.711 · scale bar 200 µm

    Fit
    GPT-6 AstraCodexS = 0.71

  • WDM-v2 · Claude Code · Claude Opus 5.5

    S = 0.683 · scale bar 200 µm

    Fit
    Opus 5.5Claude CodeS = 0.68

  • WDM-v2 · Claude Code · Claude Sonnet 5.5

    S = 0.340 · scale bar 200 µm

    Fit
    Sonnet 5.5 (high)Claude CodeS = 0.34

  • WDM-v2 · Codex · GPT-5.6-sol

    S = 0.066 · scale bar 200 µm

    Fit
    GPT-5.6 SolCodexS = 0.07

  • WDM-v2 · Codex · GPT-6.1-sol

    S = 0.056 · scale bar 200 µm

    Fit
    GPT-6.1 SolCodexS = 0.06

  • WDM-v2 · Claude Code · Claude Fable 5.1

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    Fable 5.1Claude CodeInvalid · S = 0

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

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    Gemini 4 Argonmini-SWE-agentInvalid · S = 0

  • WDM-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

  • WDM-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

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

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    GPT-6.1 Solmini-SWE-agentInvalid · S = 0

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

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    Kimi K3.1 ProClaude CodeInvalid · S = 0

  • WDM-v2 · Muse Code · Muse Wonder

    Invalid final · S = 0 · scale bar 200 µm

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

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

    Invalid final · S = 0 · scale bar 200 µm

    Fit
    Sonnet 5.5mini-SWE-agentInvalid · S = 0