Knowledge-focused evaluation on MixEval Hard
21.8Accuracy
FineInstructions
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.01 | 21.8 | |
2026.01 | 19.2 | |
2026.01 | 18.9 | |
2026.01 | 18.4 | |
2026.01 | 17.1 | |
2026.01 | 16.7 | |
2026.01 | 16.7 | |
2026.01 | 14 |
FineInstructions
| Method | Links | |
|---|---|---|
2026.01 | 21.8 | |
2026.01 | 19.2 | |
2026.01 | 18.9 | |
2026.01 | 18.4 | |
2026.01 | 17.1 | |
2026.01 | 16.7 | |
2026.01 | 16.7 | |
2026.01 | 14 |