List your company
ResearchFormerly WizWand

Instruction on IFEval

89.8ScoreQwen3.5-4B
54.4463.6272.881.98May 6, 2026May 8, 2026May 10, 2026May 12, 2026May 14, 2026May 16, 2026May 18, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Qwen3.5-4BActive / Total Parameters=4.0B / 4.0B, Sampling Settings=Recommended sampling settings2026.0589.8
Gemma-4-E4B-itActive / Total Parameters=4.0B / 8.0B, Sampling Settings=Recommended sampling settings2026.0588.5
Qwen3-4B-Thinking-2507Active / Total Parameters=4.0B / 4.0B, Sampling Settings=Recommended sampling settings2026.0586.8
ZAYA1-8BActive / Total Parameters=0.7B / 8.0B, Sampling Settings=T=1.0, top-p=0.95, top-k disabled2026.0585.6
ElasticModel=LLaDA2.0-mini2026.0585.03
Qwen2.5-72BParameters=72B2026.0584.3
BaselineModel=LLaDA2.0-mini2026.0583.55
Qwen2.5-14BParameters=14B2026.0581.6
FORGE-7B-MATHParameters=7B, Configuration=MATH2026.0580.5
FORGE-7B-NPParameters=7B, Configuration=NP2026.0579.6
Qwen2.5-32BParameters=32B2026.0579.5
FORGE-7B-NP-MATHParameters=7B, Configuration=NP-MATH2026.0579.3
Qwen2.5-7BParameters=7B2026.0573.5
InternLM3-8BParameters=8B2026.0572.5
LLama3.1-8bParameters=8B2026.0569.3
Qwen2.5-3BParameters=3B2026.0559.1
Qwen2.5-7B-SFTParameters=7B, Configuration=SFT2026.0555.8