Scientific Research on FrontierScience Research track
53.3Score (%)EvoMaster
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EvoMasterBackend Model=GPT-5.4, Maximum Runtime=24 hours2026.04 | 53.3 | 191 | |
| OpenClawBackend Model=GPT-5.4, Maximum Runtime=24 hours2026.04 | 18.3 | — | |
| GPT-5-mini High2026.06 | 18.3 | — | |
| Seed2.0 Lite2026.06 | 18.3 | — | |
| Gemini-3-Flash High2026.06 | 11.7 | — |