Scientific Coding on ScienceAgentBench deterministic-eval 2024
47.4Pass Rate
Deep negative knowledge retry
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 47.4 | 795 | ||
2026.06 | 44.7 | 1,109 | |
2026.06 | 36.8 | 296 | |
2026.06 | 31.6 | - | |
2026.06 | 31.6 | - |
Deep negative knowledge retry
| Method | Links | ||
|---|---|---|---|
| 47.4 | 795 | ||
2026.06 | 44.7 | 1,109 | |
2026.06 | 36.8 | 296 | |
2026.06 | 31.6 | - | |
2026.06 | 31.6 | - |