Physical Diagram Generation on PhyDrawGen Open Voc. (test)
48.9Preference RatePhyDrawGen
Evaluation results
| Method | Links | |
|---|---|---|
| PhyDrawGenEvaluation Protocol=Human-judge forced-choice comparison2026.05 | 48.9 | |
| Gemini 3 ProEvaluation Protocol=Human-judge forced-choice comparison2026.05 | 23.4 | |
| GPT-5Evaluation Protocol=Human-judge forced-choice comparison2026.05 | 21.5 | |
| Gemini 2.5 FlashEvaluation Protocol=Human-judge forced-choice comparison2026.05 | 6.2 |