IFEval

Safety

Instruction Following Evaluation — tests adherence to verifiable instructions

Higher is better

Rank	Model	Provider	Score
1	Meta: Llama 3.3 70B Instruct	Meta	90.0%
2	Meta: Llama 3.1 70B Instruct	Meta	86.7%
3	MaziyarPanahi/calme-2.1-qwen2.5-72b	MaziyarPanahi	86.6%
4	VAGOsolutions/Llama-3.1-SauerkrautLM-70b-Instruct	VAGOsolutions	86.6%
5	Qwen/Qwen2.5-72B-Instruct	Alibaba	86.4%
6	huihui-ai/Qwen2.5-72B-Instruct-abliterated	huihui-ai	85.9%
7	YOYO-AI/ZYH-LLM-Qwen2.5-14B-V3	YOYO-AI	85.8%
8	pankajmathur/orca_mini_v8_1_70b	pankajmathur	85.7%
9	dnhkng/RYS-Llama3.1-Large	dnhkng	84.9%
10	rubenroy/Gilgamesh-72B	rubenroy	84.9%
11	MaziyarPanahi/calme-2.2-qwen2.5-72b	MaziyarPanahi	84.8%
12	raphgg/test-2.5-72B	raphgg	84.4%
13	rombodawg/Rombos-LLM-V2.6-Qwen-14b	rombodawg	84.3%
14	ssmits/Qwen2.5-95B-Instruct	ssmits	84.3%
15	tensopolis/virtuoso-small-v2-tensopolis-v1	tensopolis	84.2%
16	upstage/solar-pro-preview-instruct	Upstage	84.2%
17	Qwen/Qwen2.5-14B-Instruct-1M	Alibaba	84.1%
18	mistralai/Mistral-Large-Instruct-2411	Mistral AI	84.0%
19	YOYO-AI/Qwen2.5-14B-1M-YOYO-V3	YOYO-AI	84.0%
20	YOYO-AI/Qwen2.5-14B-YOYO-V4	YOYO-AI	84.0%
21	LGAI-EXAONE/EXAONE-3.5-32B-Instruct	LG AI Research	83.9%
22	pankajmathur/orca_mini_v9_2_70b	pankajmathur	83.8%
23	allenai/Llama-3.1-Tulu-3-70B	Meta	83.8%
24	allenai/Llama-3.1-Tulu-3-70B	Ai2	83.8%
25	YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4	YOYO-AI	83.6%
26	Qwen/Qwen2.5-32B-Instruct	Alibaba	83.5%
27	zetasepic/Qwen2.5-32B-Instruct-abliterated-v2	zetasepic	83.3%
28	CombinHorizon/zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES	CombinHorizon	83.3%
29	huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2	huihui-ai	83.3%
30	vicgalle/Configurable-Llama-3.1-8B-Instruct	vicgalle	83.1%
31	Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4	Goekdeniz-Guelmez	82.9%
32	allenai/Llama-3.1-Tulu-3-70B-DPO	Ai2	82.8%
33	arcee-ai/Virtuoso-Small-v2	Arcee AI	82.7%
34	allenai/Llama-3.1-Tulu-3-8B	Meta	82.5%
35	allenai/Llama-3.1-Tulu-3-8B	Ai2	82.5%
36	maldv/Awqward2.5-32B-Instruct	maldv	82.5%
37	Saxo/Linkbricks-Horizon-AI-Avengers-V3-32B	Saxo	82.5%
38	CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES	CombinHorizon	82.4%
39	prithivMLmods/Dinobot-Opus-14B-Exp	prithivMLmods	82.4%
40	sthenno-com/miscii-14b-1028	sthenno	82.4%
41	tanliboy/lambda-qwen2.5-14b-dpo-test	tanliboy	82.3%
42	nbeerbower/llama3.1-kartoffeldes-70B	nbeerbower	82.3%
43	YOYO-AI/Qwen2.5-14B-it-restore	YOYO-AI	82.1%
44	Saxo/Linkbricks-Horizon-AI-Avengers-V6-32B	Saxo	82.1%
45	MaziyarPanahi/calme-2.2-llama3-70b	MaziyarPanahi	82.1%
46	CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES	CombinHorizon	82.1%
47	YOYO-AI/Qwen2.5-14B-YOYO-V4-p1	YOYO-AI	82.0%
48	v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno	v000000	82.0%
49	CombinHorizon/huihui-ai-abliteratedV2-Qwen2.5-14B-Inst-BaseMerge-TIES	CombinHorizon	81.8%
50	dfurman/CalmeRys-78B-Orpo-v0.1	dfurman	81.6%

Access this data

JSON GET /api/v1

[
  {
    "rank": 1,
    "model": "Meta: Llama 3.3 70B Instruct",
    "provider": "Meta",
    "score": "89.97581971391463"
  },
  {
    "rank": 2,
    "model": "Meta: Llama 3.1 70B Instruct",
    "provider": "Meta",
    "score": "86.6885419575615"
  },
  {
    "rank": 3,
    "model": "MaziyarPanahi/calme-2.1-qwen2.5-72b",
    "provider": "MaziyarPanahi",
    "score": "86.62360315075111"
  }
]

Curl

$ curl -s https://rightrank.ai/api/v1/rankings/ifeval.json | jq '.[:3]'

CLI brew install rightrank

$ rightrank top ifeval --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category ifeval
$ rightrank value ifeval  # best performance per dollar

Claude Code Skill Skill

# In Claude Code, use the RightRank skill:
/rightrank best model for ifeval
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on ifeval