Reasoning on GPQA (Acc@1, Avg. Perf.)
44Accuracy@1 (GPQA)
DisambiguSLM
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 44 | 68.6 | |
2026.04 | 43.6 | 66.9 | |
2026.04 | 43.3 | 66.6 | |
2026.04 | 42.4 | 65 | |
2026.04 | 41.6 | 63.8 | |
2026.04 | 41.6 | 66.3 | |
2026.04 | 41.3 | 65 | |
2026.04 | 41.1 | 64.8 | |
2026.04 | 41.1 | 66 | |
2026.04 | 40.9 | 64.5 | |
2026.04 | 40.5 | 64.8 | |
2026.04 | 40.2 | 61.1 | |
2026.04 | 40.2 | 63.9 | |
2026.04 | 40.1 | 63.9 | |
2026.04 | 40 | 64 | |
2026.04 | 39.8 | 62.3 | |
2026.04 | 39.6 | 63.1 | |
2026.04 | 39.1 | 61.4 | |
2026.04 | 38.9 | 61.6 | |
2026.04 | 38.7 | 61.2 | |
2026.04 | 38.6 | 62.7 | |
2026.04 | 38.5 | 62.4 | |
2026.04 | 38.2 | 60.4 | |
2026.04 | 38.2 | 62 | |
2026.04 | 38.1 | 62.2 | |
2026.04 | 38 | 61.7 | |
2026.04 | 37.9 | 58.8 | |
2026.04 | 37.6 | 61.4 | |
2026.04 | 37.5 | 61.6 | |
2026.04 | 37.1 | 57.93 | |
2026.04 | 36.9 | 60.9 | |
2026.04 | 36.4 | 59.2 | |
2026.04 | 35.8 | 58.2 |