Knowledge Evaluation on KMMLU, KMMLU Pro, GPQA Diamond, and Related Benchmarks
85.1Accuracy
DeepSeek-V3.1
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.01 | 85.1 | |
2026.01 | 84.9 | |
2026.01 | 84.9 | |
2026.01 | 84.5 | |
2026.01 | 82.9 | |
2026.01 | 81.5 | |
2026.01 | 80.2 | |
2026.01 | 79.9 | |
2026.01 | 78.2 | |
2026.01 | 78 | |
2026.01 | 77.9 | |
2026.01 | 77.9 | |
2026.01 | 76.5 | |
2026.01 | 75.9 | |
2026.01 | 74 | |
2026.01 | 71.8 | |
2026.01 | 71.4 | |
2026.01 | 68.1 | |
2026.01 | 59.7 | |
2026.01 | 59.2 | |
2026.01 | 48.8 |