Instruction Following on Arena Hard
98.11Win Rate
OpenAI/GPT-5
Updated 21h ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.09 | 98.11 | - | - | |
2026.02 | 94.9 | - | - | |
2025.01 | 92.3 | - | - | |
2025.01 | 92 | - | - | |
2025.07 | 89.8 | - | - | |
2025.09 | 88.71 | - | - | |
2025.07 | 87.1 | - | - | |
| 87 | - | - | ||
2025.09 | 86.98 | - | - | |
2025.07 | 86 | - | - | |
2025.01 | 85.5 | - | - | |
2025.01 | 85.2 | - | - | |
| 85 | - | - | ||
2025.07 | 81.4 | - | - | |
2025.01 | 80.4 | - | - | |
2025.03 | 79.3 | - | - | |
2025.03 | 79.2 | - | - | |
2025.09 | 77.58 | - | - | |
2025.03 | 74.8 | - | - | |
2026.04 | 74.6 | - | - | |
2025.07 | 74.2 | - | - | |
2026.02 | 74.1 | - | - | |
2026.04 | 71.8 | - | - | |
2025.09 | 71.34 | - | - | |
2026.04 | 70.1 | - | - | |
2025.03 | 69.3 | - | - | |
2025.03 | 62.4 | - | - | |
2025.07 | 62.1 | - | - | |
2025.07 | 62.1 | - | - | |
2025.07 | 61.6 | - | - | |
2026.05 | 61.6 | - | - | |
2025.09 | 59.4 | - | - | |
2025.09 | 59.21 | - | - | |
2025.07 | 59.2 | - | - | |
2026.05 | 59.2 | - | - | |
2025.07 | 59.1 | - | - | |
2025.09 | 58.9 | - | - | |
2025.09 | 58.8 | - | - | |
2026.02 | 58.7 | - | - | |
2025.09 | 58.4 | - | - | |
2026.02 | 58 | - | - | |
2025.09 | 57.9 | - | - | |
2025.09 | 57.8 | - | - | |
2025.09 | 57.8 | - | - | |
2025.07 | 57.5 | - | - | |
2025.07 | 56.9 | - | - | |
2025.03 | 55.7 | - | - | |
2025.09 | 55.2 | - | - | |
2026.01 | 55.1 | - | - | |
2026.05 | 54.98 | - | - | |
2026.05 | 54.94 | - | - | |
2025.07 | 54.5 | - | - | |
2025.06 | 54.1 | - | - | |
2026.04 | 54.09 | - | - | |
2026.05 | 53.98 | - | - | |
2025.09 | 53.8 | - | - | |
2025.09 | 53.5 | - | - | |
2026.01 | 52.8 | - | - | |
2025.07 | 52.3 | - | - | |
2025.09 | 52.26 | - | - | |
2026.05 | 52.07 | - | - | |
2026.05 | 52.06 | - | - | |
2025.09 | 51.17 | - | - | |
2025.09 | 50.93 | - | - | |
2026.01 | 50.9 | - | - | |
2026.05 | 50.5 | - | - | |
2025.09 | 50.34 | - | - | |
2026.04 | 50.17 | - | - | |
2026.05 | 49.72 | - | - | |
2026.05 | 48.98 | - | - | |
2025.09 | 48.03 | - | - | |
2026.05 | 47.01 | - | - | |
2025.07 | 46.9 | - | - | |
2026.05 | 46.9 | - | - | |
2025.09 | 46.2 | - | - | |
2025.09 | 45.63 | - | - | |
2025.07 | 45.5 | - | - | |
2026.05 | 45.5 | - | - | |
2025.09 | 45.04 | - | - | |
2025.09 | 44.97 | - | - | |
2026.05 | 44.64 | - | - | |
2025.09 | 43.89 | - | - | |
2026.01 | 43.8 | - | - | |
2026.01 | 43.6 | - | - | |
2025.07 | 43.6 | - | - | |
2024.10 | 43.2 | - | - | |
2025.07 | 42.9 | - | - | |
2026.05 | 42.9 | - | - | |
2026.05 | 42.76 | - | - | |
2026.01 | 42.7 | - | - | |
2025.09 | 42.1 | - | - | |
2026.05 | 41.91 | - | - | |
2026.04 | 41.3 | - | - | |
2025.09 | 40.98 | - | - | |
2025.09 | 39.16 | - | - | |
2026.05 | 38.54 | - | - | |
2025.05 | 38.4 | - | 682 | |
2026.05 | 37.57 | - | - | |
2025.07 | 36.6 | - | - | |
2026.05 | 36.6 | - | - |
Showing 100 of 263 rows