Reasoning on ARC Challenge (exact_match, flexible_extract)
95.1Exact Match Accuracy
GPT-5 nano
Updated 23d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 95.1 | - | |
2026.05 | 90.5 | - | |
2026.05 | 90 | - | |
2026.05 | 89.6 | - | |
2026.05 | 88.1 | - | |
2026.05 | 88 | - | |
2026.05 | 81.7 | - | |
2026.05 | 80.9 | - | |
2026.05 | 75.7 | - | |
2026.05 | 75.6 | - | |
2026.05 | 71 | - | |
2026.05 | 65.9 | - | |
2026.05 | 45.7 | - | |
2026.05 | 45.5 | - | |
2026.05 | 39.8 | - | |
2026.05 | 26.2 | - | |
2026.05 | - | 87.2 | |
2026.05 | - | 56.2 | |
2026.05 | - | 25.4 | |
2026.05 | - | 74.1 | |
2026.05 | - | 75.4 | |
2026.05 | - | 93 | |
2026.05 | - | 95.1 | |
2026.05 | - | 73.7 | |
2026.05 | - | 80.5 | |
2026.05 | - | 77.8 | |
2026.05 | - | 92.3 | |
2026.05 | - | 94.2 | |
2026.05 | - | 94.4 | |
2026.05 | - | 54.9 | |
2026.05 | - | 95.4 | |
2026.05 | - | 78.9 |