AA-IFBench leaderboard

A display-only Artificial Analysis IFBench score.

Models ranked by their published Artificial Analysis IFBench value

Rank	Model	Provider	Constraint satisfaction accuracy
1	MiniMax M3	MiniMax	82.9
2	Nemotron 3 Ultra	NVIDIA	81.4
3	Grok 4.3	xAI	81.3
4	Qwen3.7 Max	Alibaba	80.5
5	MiMo-V2.5-Pro	Xiaomi	79.9
6	Qwen3.7 Plus	Alibaba	78.0
7	GPT-5.2-Codex	OpenAI	77.6
8	Gemini 3.1 Pro	Google	77.1
9	Qwen 3.6 Max (preview)	Alibaba	76.6
10	DeepSeek V4 Pro 0813	DeepSeek	76.5
11	Gemini 3.5 Flash	Google	76.3
11	GLM-5.1	Z.AI	76.3
13	Kimi K2.6	Moonshot AI	76.0
14	GPT-5.4 nano	OpenAI	75.9
14	GPT-5.5	OpenAI	75.9
14	Muse Spark	Meta	75.9
17	MiniMax M2.7	MiniMax	75.7
17	Qwen3.5-122B-A10B	Alibaba	75.7
19	Gemma 4 31B	Google	75.6
19	Qwen3.5-27B	Alibaba	75.6
21	GPT-5.2	OpenAI	75.4
21	GPT-5.3 Codex	OpenAI	75.4
23	Qwen3.6 Plus	Alibaba	75.2
24	Command A+	Cohere	73.9
24	GPT-5.4	OpenAI	73.9
26	Gemma 4 12B	Google	73.5
27	GLM-5.2	Z.AI	73.3
27	GPT-5.4 mini	OpenAI	73.3
29	GLM-5-Turbo	Z.AI	73.2
30	GPT-5 (high)	OpenAI	73.1
31	GPT-5.1	OpenAI	72.9
32	GPT-5.6 Sol	OpenAI	72.7
33	Qwen3.5-35B-A3B	Alibaba	72.5
34	Gemma 4 26B A4B	Google	72.4
35	GLM-5	Z.AI	72.3
36	Nemotron 3 Super 100B	NVIDIA	71.5
37	o3	OpenAI	71.4
38	GPT-5.6 Terra	OpenAI	71.2
38	Solar Pro 3	Upstage	71.2
40	Nemotron 3 Nano 30B	NVIDIA	71.1
41	GPT-5 (medium)	OpenAI	70.6
42	Gemini 3 Pro	Google	70.4
43	o1	OpenAI	70.3
44	Kimi K2.5	Moonshot AI	70.2
44	Kimi K2.5 (Reasoning)	Moonshot AI	70.2
46	GPT-5.1-Codex	OpenAI	70.0
46	GPT-5.1-Codex-Max	OpenAI	70.0
48	GPT-OSS 120B	OpenAI	69.0
49	MiMo-V2-Pro	Xiaomi	68.8
49	Mistral Medium 3.5 128B	Mistral	68.8
51	GLM-4.7	Z.AI	67.9
52	Qwen3.6-27B	Alibaba	67.6
53	Step 3.7 Flash	StepFun	67.3
54	GPT-OSS 20B	OpenAI	65.1
55	K-Exaone	LG AI Research	64.7
56	Qwen3.6-35B-A3B	Alibaba	64.4
57	Claude Fable 5	Anthropic	63.5
58	Nemotron 3 Nano Omni 30B A3B	NVIDIA	63.2
59	Kimi K2.7 Code	Moonshot AI	63.1
60	Claude Opus 4.8	Anthropic	62.2
61	GLM-5V-Turbo	Z.AI	61.1
62	Claude Opus 4.7 (Adaptive)	Anthropic	58.6
63	Claude Opus 4.5 Thinking	Anthropic	58.0
64	North Mini Code	Cohere	57.6
65	Ling 2.6 Flash	InclusionAI	57.4
66	Trinity-Large-Preview	Arcee AI	56.3
66	Trinity-Large-Thinking	Arcee AI	56.3
68	LFM2.5-8B-A1B	LiquidAI	55.6
69	Claude 4.1 Opus Thinking	Anthropic	55.4
70	Gemini 3 Flash	Google	55.1
71	Grok 4	xAI	53.7
72	MiMo-V2-Omni	Xiaomi	53.5
73	Claude Opus 4.6 (Adaptive)	Anthropic	53.1
74	Grok 4.1 Fast (Reasoning)	xAI	52.7
75	Qwen3.5 397B	Alibaba	51.6
75	Qwen3.5 397B (Reasoning)	Alibaba	51.6
77	Grok 4 Fast (Reasoning)	xAI	50.5
78	DeepSeek V3.2	DeepSeek	49.0
79	Gemini 2.5 Pro	Google	48.7
80	Mistral Small 4	Mistral	48.2
80	Mistral Small 4 (Reasoning)	Mistral	48.2
82	FAUltravox v0.6 Llama 3.3 70B	Fixie AI	47.1
83	Claude 4 Sonnet	Anthropic	45.4
84	Claude Opus 4.6	Anthropic	44.6
85	Gemma 4 E4B	Google	44.2
86	Qwen3 Max	Alibaba	44.1
87	Claude Opus 4.7	Anthropic	43.6
88	Qwen3-Omni-30B-A3B-Thinking	Alibaba	43.4
89	Claude Opus 4.5	Anthropic	43.0
89	GPT-4.1	OpenAI	43.0
89	Llama 4 Maverick	Meta	43.0
92	DeepSeek V3.1 (Reasoning)	DeepSeek	41.5
92	Kimi K2	Moonshot AI	41.5
94	Grok Code Fast 1	xAI	41.4
95	Claude Sonnet 4.6	Anthropic	41.2
96	MiMo-V2-Flash	Xiaomi	39.9
97	DeepSeek-R1	DeepSeek	39.6
98	Llama 4 Scout	Meta	39.5
99	Mistral Medium 3	Mistral	39.3
100	Gemini 2.5 Flash	Google	39.0
100	Llama 3.1 405B	Meta	39.0
102	GPT-4.1 mini	OpenAI	38.3
103	Nemotron Ultra 253B	NVIDIA	38.2
104	Nova Pro	Amazon	38.1
105	Gemma 4 E2B	Google	38.0
106	DeepSeek V3.1	DeepSeek	37.8
107	GLM-4.5-Air	Z.AI	37.6
108	GLM-4.6	Z.AI	36.7
109	Grok 4.1 Fast	xAI	36.5
110	Mistral Large 3	Mistral	36.2
111	Claude 3 Haiku	Anthropic	36.1
112	DeepSeek V3	DeepSeek	34.8
113	SASarvam 105B	Sarvam	34.4
114	GPT-4o	OpenAI	34.3
115	Solar Pro 2	Upstage	33.7
116	Exaone 4.0 32B	LG AI Research	33.5
117	LFM2.5-VL-1.6B-Extract	LiquidAI	33.1
118	GPT-4.1 nano	OpenAI	32.0
119	Gemma 3 27B	Google	31.8
120	Mistral Large 2	Mistral	31.2
120	Qwen3-Omni-30B-A3B-Instruct	Alibaba	31.2
122	GPT-4o mini	OpenAI	31.0
123	SASarvam 30B	Sarvam	26.5
124	Granite-4.0-H-1B	IBM	26.2
125	Exaone 4.0 1.2B	LG AI Research	25.3
126	Phi-4	Microsoft	23.5
127	DeepSeek R1 Distill Qwen 32B	DeepSeek	22.9
128	Granite-4.0-1B	IBM	20.5
129	Granite-4.0-H-350M	IBM	17.6
130	Granite-4.0-350M	IBM	15.9

Evidence key: ObservedLast good

Rows are ordered by the value Artificial Analysis IFBench Benchmark Leaderboard published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.