IFEval — Results

Rank	Model	Score
1	lfm2-5-24b-a2b	96.75
2	minicpm5-2b	86.7
3	lfm2-5-vl-3b	82.3
4	north-micro-vision-instruct	74.9
5	qwen3-5-27b	0.95
6	qwen3-7-plus	0.946
7	qwen3-6-plus	0.943
8	qwen3-7-max	0.943
9	o3-mini	0.939
10	qwen3-5-122b-a10b	0.934
11	qwen3-5-397b-a17b	0.926
12	llama-3-3-70b-instruct	0.921
13	qwen3-5-35b-a3b	0.919
14	qwen3-5-9b	0.915
15	kimi-k2-instruct-0905	0.898
16	kimi-k2-instruct	0.898
17	qwen3-5-4b	0.898
18	llama-3-1-nemotron-ultra-253b-v1	0.894
19	qwen3-235b-a22b-instruct-2507	0.887
20	llama-3-1-405b-instruct	0.886
21	gpt-4-1	0.874
22	deepseek-v3	0.861
23	phi-4-reasoning-plus	0.849
24	gpt-4-1-mini	0.841
25	qwen2-5-72b-instruct	0.841

IFEval — Evaluations

1 phaseActive

No evaluations yet for this benchmark.