General Reasoning on MMLU & GPQA
62.62Average ScoreINSIGHT
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTModel=Qwen3-4B2026.03 | 62.62 | |
| MOPPSModel=Qwen3-4B2026.03 | 62.17 | |
| EXPECTED-DIFFICULTYModel=Qwen3-4B2026.03 | 62.17 | |
| INVERSE-EVIDENCEModel=Qwen3-4B2026.03 | 62.16 | |
| RANDOMModel=Qwen3-4B2026.03 | 62.14 | |
| INSIGHTModel=Qwen3-1.7B2026.03 | 51.96 | |
| INVERSE-EVIDENCEModel=Qwen3-1.7B2026.03 | 51.48 | |
| RANDOMModel=Qwen3-1.7B2026.03 | 51.36 | |
| MOPPSModel=Qwen3-1.7B2026.03 | 51.35 | |
| INSIGHTModel=Qwen3-0.6B2026.03 | 42.14 | |
| RANDOMModel=Qwen3-0.6B2026.03 | 41.13 | |
| MOPPSModel=Qwen3-0.6B2026.03 | 40.8 | |
| INVERSE-EVIDENCEModel=Qwen3-0.6B2026.03 | 39.98 |