| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-copa-zero-shot | Taylor-Calibrate qwen3_8b 100M_ga_s2_taylor | #2 | Accuracy: 87.0 |
| common-sense-reasoning-on-arc-easy | Taylor-Calibrate qwen3_8b 700M_ga_s2_taylor | #19 | Accuracy: 80.72 |
| question-answering-on-boolq | Taylor-Calibrate qwen3_8b 700M_uniform_taylor | #28 | Accuracy: 84.56 |
| question-answering-on-piqa | Taylor-Calibrate qwen2_3b 100M_ga_s2_taylor | #70 | Accuracy: 78.4 |
| sentence-completion-on-hellaswag | Taylor-Calibrate qwen3_8b 700M_uniform_taylor | #97 | Accuracy: 74.37 |