Comprehensive cognitive reasoning on BBH
40.65BBH Comprehensive Reasoning ScoreQwen-0.6B-Base
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen-0.6B-BaseTraining Tokens=N/A, Inference Top-K=N/A2026.01 | 40.65 | |
| DenseTraining Tokens=20B, Inference Top-K=N/A2026.01 | 38.81 | |
| InfLLM v2Training Tokens=20B, Inference Top-K=N/A2026.01 | 38.07 | |
| PHSATraining Tokens=20B, Inference Top-K=N/A2026.01 | 37.83 | |
| Qwen-0.6B-BaseTraining Tokens=N/A, Inference Top-K=22026.01 | 36.25 | |
| PHSATraining Tokens=20B, Inference Top-K=22026.01 | 34.71 | |
| InfLLM v2Training Tokens=20B, Inference Top-K=22026.01 | 34.39 | |
| DenseTraining Tokens=20B, Inference Top-K=22026.01 | 32.13 |