Agent Evaluation on OpenThoughts TBLite
72.1Accuracy
Kimi-K2.5
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 72.1 | |
2026.06 | 41.3 | |
2026.06 | 25.8 | |
2026.06 | 10.9 | |
2026.06 | 3.2 |
Kimi-K2.5
| Method | Links | |
|---|---|---|
2026.06 | 72.1 | |
2026.06 | 41.3 | |
2026.06 | 25.8 | |
2026.06 | 10.9 | |
2026.06 | 3.2 |