Instruction on IFEval
89.8ScoreQwen3.5-4B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-4BActive / Total Parameters=4.0B / 4.0B, Sampling Settings=Recommended sampling settings2026.05 | 89.8 | |
| Gemma-4-E4B-itActive / Total Parameters=4.0B / 8.0B, Sampling Settings=Recommended sampling settings2026.05 | 88.5 | |
| Qwen3-4B-Thinking-2507Active / Total Parameters=4.0B / 4.0B, Sampling Settings=Recommended sampling settings2026.05 | 86.8 | |
| ZAYA1-8BActive / Total Parameters=0.7B / 8.0B, Sampling Settings=T=1.0, top-p=0.95, top-k disabled2026.05 | 85.6 | |
| ElasticModel=LLaDA2.0-mini2026.05 | 85.03 | |
| Qwen2.5-72BParameters=72B2026.05 | 84.3 | |
| BaselineModel=LLaDA2.0-mini2026.05 | 83.55 | |
| Qwen2.5-14BParameters=14B2026.05 | 81.6 | |
| FORGE-7B-MATHParameters=7B, Configuration=MATH2026.05 | 80.5 | |
| FORGE-7B-NPParameters=7B, Configuration=NP2026.05 | 79.6 | |
| Qwen2.5-32BParameters=32B2026.05 | 79.5 | |
| FORGE-7B-NP-MATHParameters=7B, Configuration=NP-MATH2026.05 | 79.3 | |
| Qwen2.5-7BParameters=7B2026.05 | 73.5 | |
| InternLM3-8BParameters=8B2026.05 | 72.5 | |
| LLama3.1-8bParameters=8B2026.05 | 69.3 | |
| Qwen2.5-3BParameters=3B2026.05 | 59.1 | |
| Qwen2.5-7B-SFTParameters=7B, Configuration=SFT2026.05 | 55.8 |