Benchmark Explorer

Compare 406 AI models across four benchmark categories: reasoning, code generation, language understanding, and tool use. Scores are derived from model capabilities and composite rankings.

Total Models

406

With Reasoning

270

With Vision

232

Avg Score

Top Models by Average Benchmark Score

LMMarketCap.com

Benchmark Categories

Top models in each benchmark category, scored on capability support and composite ranking data.

Reasoning

Chain-of-thought reasoning, logic, and mathematical problem solving.

#	Model	Provider	Score
1	Claude Fable 5Anthropic	Anthropic	100
2	Claude Fable 5 (batch)Anthropic	Anthropic	100
3	Claude Opus 5 (Fast)Anthropic	Anthropic	100
4	Claude Opus 5Anthropic	Anthropic	100
5	Claude Opus 4.8 (Fast)Anthropic	Anthropic	100
6	Claude Opus 4.8Anthropic	Anthropic	100
7	Claude Opus 4.7 (Fast)Anthropic	Anthropic	100
8	Claude Opus 4.7Anthropic	Anthropic	100
9	Claude Opus 4.7 (batch)Anthropic	Anthropic	100
10	Claude Opus 4.8 (batch)Anthropic	Anthropic	100
11	GPT-5.5 ProOpenAI	OpenAI	100
12	GPT-5.5 Pro (batch)OpenAI	OpenAI	100
13	GPT-5.5OpenAI	OpenAI	100
14	GPT-5.5 (batch)OpenAI	OpenAI	100
15	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	100

Code Generation

Code writing, debugging, and software engineering tasks.

#	Model	Provider	Score
1	Claude Fable 5Anthropic	Anthropic	93
2	Claude Fable 5 (batch)Anthropic	Anthropic	93
3	Claude Opus 5 (Fast)Anthropic	Anthropic	91
4	Claude Opus 5Anthropic	Anthropic	91
5	Claude Opus 4.8 (Fast)Anthropic	Anthropic	91
6	Claude Opus 4.8Anthropic	Anthropic	91
7	Claude Opus 4.7 (Fast)Anthropic	Anthropic	91
8	Claude Opus 4.7Anthropic	Anthropic	91
9	Claude Opus 4.7 (batch)Anthropic	Anthropic	91
10	Claude Opus 4.8 (batch)Anthropic	Anthropic	91
11	GPT-5.5 ProOpenAI	OpenAI	89
12	GPT-5.5 Pro (batch)OpenAI	OpenAI	89
13	GPT-5.5OpenAI	OpenAI	89
14	GPT-5.5 (batch)OpenAI	OpenAI	89
15	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	89

Language Understanding

Text comprehension, multi-modal input, and information retrieval.

#	Model	Provider	Score
1	Claude Fable 5Anthropic	Anthropic	86
2	Claude Fable 5 (batch)Anthropic	Anthropic	86
3	Claude Opus 5 (Fast)Anthropic	Anthropic	85
4	Claude Opus 5Anthropic	Anthropic	85
5	Claude Opus 4.8 (Fast)Anthropic	Anthropic	85
6	Claude Opus 4.8Anthropic	Anthropic	85
7	Claude Opus 4.7 (Fast)Anthropic	Anthropic	85
8	Claude Opus 4.7Anthropic	Anthropic	85
9	Claude Opus 4.7 (batch)Anthropic	Anthropic	85
10	Claude Opus 4.8 (batch)Anthropic	Anthropic	84
11	GPT-5.5 ProOpenAI	OpenAI	83
12	GPT-5.5 Pro (batch)OpenAI	OpenAI	83
13	GPT-5.5OpenAI	OpenAI	83
14	GPT-5.5 (batch)OpenAI	OpenAI	83
15	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	83

Tool Use

Function calling, structured output, and agentic workflows.

#	Model	Provider	Score
1	Claude Fable 5Anthropic	Anthropic	98
2	Claude Fable 5 (batch)Anthropic	Anthropic	98
3	Claude Opus 5 (Fast)Anthropic	Anthropic	98
4	Claude Opus 5Anthropic	Anthropic	98
5	Claude Opus 4.8 (Fast)Anthropic	Anthropic	98
6	Claude Opus 4.8Anthropic	Anthropic	98
7	Claude Opus 4.7 (Fast)Anthropic	Anthropic	98
8	Claude Opus 4.7Anthropic	Anthropic	98
9	Claude Opus 4.7 (batch)Anthropic	Anthropic	98
10	Claude Opus 4.8 (batch)Anthropic	Anthropic	98
11	GPT-5.5 ProOpenAI	OpenAI	98
12	GPT-5.5 Pro (batch)OpenAI	OpenAI	98
13	GPT-5.5OpenAI	OpenAI	98
14	GPT-5.5 (batch)OpenAI	OpenAI	98
15	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	98

Cross-Benchmark Comparison

All 406 models ranked by average score across all four benchmark categories.

Model	Provider	Code	Reasoning	Language	Tool Use	Average
Claude Fable 5Anthropic	Anthropic	93	100	86	98	94
Claude Fable 5 (batch)Anthropic	Anthropic	93	100	86	98	94
Claude Opus 5 (Fast)Anthropic	Anthropic	91	100	85	98	94
Claude Opus 5Anthropic	Anthropic	91	100	85	98	94
Claude Opus 4.8 (Fast)Anthropic	Anthropic	91	100	85	98	94
Claude Opus 4.8Anthropic	Anthropic	91	100	85	98	94
Claude Opus 4.7 (Fast)Anthropic	Anthropic	91	100	85	98	94
Claude Opus 4.7Anthropic	Anthropic	91	100	85	98	94
Claude Opus 4.7 (batch)Anthropic	Anthropic	91	100	85	98	94
Claude Opus 4.8 (batch)Anthropic	Anthropic	91	100	84	98	93
GPT-5.5 ProOpenAI	OpenAI	89	100	83	98	93
GPT-5.5 Pro (batch)OpenAI	OpenAI	89	100	83	98	93
GPT-5.5OpenAI	OpenAI	89	100	83	98	93
GPT-5.5 (batch)OpenAI	OpenAI	89	100	83	98	93
Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	89	100	83	98	93
Gemini 3.1 Pro PreviewGoogle	Google	89	100	83	98	93
Gemini 3.1 Pro Preview (batch)Google	Google	89	100	83	98	93
GPT-5.4 ProOpenAI	OpenAI	89	100	82	98	92
GPT-5.4 Pro (batch)OpenAI	OpenAI	89	100	82	98	92
GPT-5.4OpenAI	OpenAI	89	100	82	98	92
GPT-5.4 (batch)OpenAI	OpenAI	89	100	82	98	92
Claude Opus 4.6Anthropic	Anthropic	87	100	81	98	92
Claude Opus 4.6 (batch)Anthropic	Anthropic	87	100	81	98	92
GPT-5.6 Luna ProOpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Luna Pro (batch)OpenAI	OpenAI	86	100	80	98	91
GPT-5.6 LunaOpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Luna (batch)OpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Terra ProOpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Terra Pro (batch)OpenAI	OpenAI	86	100	80	98	91
GPT-5.6 TerraOpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Terra (batch)OpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Sol ProOpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Sol Pro (batch)OpenAI	OpenAI	86	100	80	98	91
GPT-5.6 SolOpenAI	OpenAI	86	100	80	98	91
GPT-5.6 Sol (batch)OpenAI	OpenAI	86	100	80	98	91
Grok 4.3xAI	xAI	86	100	80	98	91
Grok 4.20xAI	xAI	86	100	80	98	91
GPT-5.3-CodexOpenAI	OpenAI	87	98	81	98	91
GPT-5.2-CodexOpenAI	OpenAI	87	98	81	98	91
Gemini 3 Flash PreviewGoogle	Google	86	100	80	98	91
Gemini 3 Flash Preview (batch)Google	Google	86	100	80	98	91
GPT-5.2 ProOpenAI	OpenAI	87	98	81	98	91
GPT-5.2 Pro (batch)OpenAI	OpenAI	87	98	81	98	91
GPT-5.2OpenAI	OpenAI	87	98	81	98	91
GPT-5.2 (batch)OpenAI	OpenAI	87	98	81	98	91
GPT-5.1-Codex-MaxOpenAI	OpenAI	86	98	80	98	91
GPT-5.1OpenAI	OpenAI	86	98	80	98	91
GPT-5.1-CodexOpenAI	OpenAI	86	98	80	98	91
GPT-5 ProOpenAI	OpenAI	86	98	80	98	91
GPT-5 Pro (batch)OpenAI	OpenAI	86	98	80	98	91
GPT-5 Codex (batch)OpenAI	OpenAI	86	98	80	98	91
GPT-5OpenAI	OpenAI	86	98	80	98	91
GPT-5 (batch)OpenAI	OpenAI	86	98	80	98	91
GPT-5.1 (batch)OpenAI	OpenAI	85	98	79	98	90
GPT-5.1-Codex-MiniOpenAI	OpenAI	85	98	79	98	90
Grok 4.5xAI	xAI	86	95	80	98	90
Claude Sonnet 5Anthropic	Anthropic	83	100	78	98	90
Claude Sonnet 4.6Anthropic	Anthropic	83	100	78	98	90
Claude Sonnet 4.6 (batch)Anthropic	Anthropic	83	100	78	98	90
o3 ProOpenAI	OpenAI	84	98	79	98	90
o3 Pro (batch)OpenAI	OpenAI	84	98	79	98	90
o3OpenAI	OpenAI	84	98	79	98	90
o3 (batch)OpenAI	OpenAI	84	98	79	98	90
Claude Opus 4.5Anthropic	Anthropic	83	98	78	98	89
Claude Opus 4.5 (batch)Anthropic	Anthropic	83	98	78	98	89
Gemini 2.5 ProGoogle	Google	82	100	76	98	89
Gemini 2.5 Pro (batch)Google	Google	82	100	76	98	89
Gemini 2.5 Pro Preview 06-05Google	Google	82	100	76	98	89
Gemini 2.5 Pro Preview 05-06Google	Google	82	100	76	98	89
Claude Sonnet 4.5Anthropic	Anthropic	81	100	76	98	89
Claude Sonnet 4.5 (batch)Anthropic	Anthropic	81	100	76	98	89
Muse Spark 1.2meta	meta	79	100	74	98	88
Gemini 3.6 FlashGoogle	Google	79	100	74	98	88
Gemini 3.6 Flash (batch)Google	Google	79	100	74	98	88
Muse Spark 1.1meta	meta	79	100	74	98	88
o4 Mini High (batch)OpenAI	OpenAI	80	98	75	98	88
o4 MiniOpenAI	OpenAI	80	98	75	98	88
o4 Mini (batch)OpenAI	OpenAI	80	98	75	98	88
Gemini 3.1 Flash Lite PreviewGoogle	Google	78	100	74	98	88
Gemini 3.5 FlashGoogle	Google	78	100	73	98	87
Gemini 3.5 Flash (batch)Google	Google	78	100	73	98	87
Gemini 2.5 Flash LiteGoogle	Google	78	100	73	98	87
Gemini 2.5 Flash Lite (batch)Google	Google	78	100	73	98	87
Gemini 2.5 FlashGoogle	Google	78	100	73	98	87
Gemini 2.5 Flash (batch)Google	Google	78	100	73	98	87
GPT-5.4 NanoOpenAI	OpenAI	78	98	74	98	87
GPT-5.4 Nano (batch)OpenAI	OpenAI	78	98	74	98	87
GPT-5.4 MiniOpenAI	OpenAI	78	98	74	98	87
GPT-5.4 Mini (batch)OpenAI	OpenAI	78	98	74	98	87
Gemini 3.5 Flash LiteGoogle	Google	77	100	72	98	87
Gemini 3.5 Flash Lite (batch)Google	Google	77	100	72	98	87
GPT-5 Mini (batch)OpenAI	OpenAI	76	98	72	98	86
GPT-5 Nano (batch)OpenAI	OpenAI	76	98	72	98	86
Qwen3.8 MaxAlibaba	Alibaba	79	100	66	98	86
DeepSeek V4 ProDeepSeek	DeepSeek	84	100	61	98	86
Claude Opus 4.1 (batch)Anthropic	Anthropic	75	98	71	98	86
Gemma 4 31BGoogle	Google	79	98	66	98	85
Gemma 4 31B (free)Google	Google	79	98	66	98	85
Qwen3.5 397B A17BAlibaba	Alibaba	79	98	66	98	85
o1OpenAI	OpenAI	75	98	70	98	85
o1 (batch)OpenAI	OpenAI	75	98	70	98	85
Claude Opus 4.1Anthropic	Anthropic	76	98	75	90	85
Claude Opus 4Anthropic	Anthropic	76	98	75	90	85
Qwen3.7 PlusAlibaba	Alibaba	76	100	63	98	84
Qwen3.5-27BAlibaba	Alibaba	77	98	64	98	84
Qwen3.5-122B-A10BAlibaba	Alibaba	77	98	64	98	84
o4 Mini HighOpenAI	OpenAI	73	98	68	98	84
Qwen3.5 Plus 2026-04-20Alibaba	Alibaba	75	100	62	98	84
Kimi K2.6Moonshot AI	Moonshot AI	76	98	63	98	84
Qwen3.5-35B-A3BAlibaba	Alibaba	76	98	63	98	84
Inklingthinkingmachines	thinkingmachines	74	100	62	98	84
MiniMax M3MiniMax	MiniMax	74	100	62	98	84
Qwen3.6 PlusAlibaba	Alibaba	74	100	62	98	84
Claude Haiku 4.5Anthropic	Anthropic	71	98	67	98	84
Claude Haiku 4.5 (batch)Anthropic	Anthropic	71	98	67	98	84
DeepSeek V3.2DeepSeek	DeepSeek	80	98	57	98	83
MiMo-V2.5Xiaomi	Xiaomi	73	100	61	98	83
o3 MiniOpenAI	OpenAI	75	98	61	98	83
GLM 5.2Zhipu AI	Zhipu AI	78	100	55	98	83
R1 0528DeepSeek	DeepSeek	79	98	56	98	83
Gemma 4 26B A4B Google	Google	73	98	61	98	83
Gemma 4 26B A4B (free)Google	Google	73	98	61	98	83
GLM 5V TurboZhipu AI	Zhipu AI	73	98	61	98	83
Claude Sonnet 4Anthropic	Anthropic	70	100	70	90	83
o3 Mini High (batch)OpenAI	OpenAI	74	98	60	98	83
o3 Mini (batch)OpenAI	OpenAI	74	98	60	98	83
MiniMax M3 (batch)MiniMax	MiniMax	74	95	62	98	82
GLM 5.1Zhipu AI	Zhipu AI	77	98	55	98	82
MiniMax M2.7MiniMax	MiniMax	77	98	55	98	82
GLM 5 TurboZhipu AI	Zhipu AI	77	98	55	98	82
MiniMax M2.5MiniMax	MiniMax	77	98	55	98	82
GLM 5Zhipu AI	Zhipu AI	77	98	55	98	82
MiMo-V2.5-ProXiaomi	Xiaomi	76	100	53	98	82
GLM 5.2 (batch)Zhipu AI	Zhipu AI	78	95	55	98	82
Qwen3.5-FlashAlibaba	Alibaba	70	100	58	98	82
Qwen3.5 Plus 2026-02-15Alibaba	Alibaba	70	100	58	98	82
Qwen3 VL 235B A22B ThinkingAlibaba	Alibaba	71	98	59	98	82
Qwen3.7 MaxAlibaba	Alibaba	75	100	52	98	81
Mistral Medium 3.5Mistral AI	Mistral AI	72	95	60	98	81
GPT-5 MiniOpenAI	OpenAI	66	98	63	98	81
GLM 4.7Zhipu AI	Zhipu AI	75	98	53	98	81
GLM 4.6Zhipu AI	Zhipu AI	75	98	53	98	81
GLM 4.5Zhipu AI	Zhipu AI	75	98	53	98	81
Qwen3.6 Max PreviewAlibaba	Alibaba	75	98	52	98	81
Hy3Tencent	Tencent	74	98	52	98	81
R1DeepSeek	DeepSeek	74	98	52	98	81
Qwen3.5-9BAlibaba	Alibaba	68	98	57	98	80
MiniMax M2.1MiniMax	MiniMax	73	98	50	98	80
GLM 4.6VZhipu AI	Zhipu AI	67	98	56	98	80
MiniMax M2MiniMax	MiniMax	73	98	50	98	80
DeepSeek V3.2 ExpDeepSeek	DeepSeek	72	98	50	98	80
DeepSeek V3.1DeepSeek	DeepSeek	72	98	50	98	80
Inkling Smallthinkingmachines	thinkingmachines	67	98	60	90	79
DeepSeek V3.1 TerminusDeepSeek	DeepSeek	70	98	49	98	79
o3 Mini HighOpenAI	OpenAI	66	98	53	98	79
Inkling (batch)thinkingmachines	thinkingmachines	68	95	61	90	79
Qwen3 Max ThinkingAlibaba	Alibaba	70	98	48	98	79
Qwen3 Next 80B A3B ThinkingAlibaba	Alibaba	69	98	47	98	78
GLM 4.5VZhipu AI	Zhipu AI	65	93	54	98	78
Kimi K2.5Moonshot AI	Moonshot AI	62	98	51	98	77
Grok 4.20 Multi-AgentxAI	xAI	85	100	80	43	77
Trinity Large Thinkingarcee-ai	arcee-ai	66	98	45	98	77
GLM 4.7 FlashZhipu AI	Zhipu AI	66	98	45	98	77
MiniMax M1MiniMax	MiniMax	67	100	50	90	77
Qwen3 30B A3BAlibaba	Alibaba	66	98	45	98	77
Qwen3 235B A22B Thinking 2507Alibaba	Alibaba	67	95	46	98	77
GPT-5.3 ChatOpenAI	OpenAI	77	48	81	98	76
GPT-5.2 ChatOpenAI	OpenAI	77	48	81	98	76
GLM 4.5 AirZhipu AI	Zhipu AI	67	98	49	90	76
Mercury 2Inception	Inception	64	98	43	98	76
Kimi K2.7 CodeMoonshot AI	Moonshot AI	58	98	48	98	76
Qwen3 30B A3B Thinking 2507Alibaba	Alibaba	66	93	45	98	76
Nova 2 LiteAmazon	Amazon	58	100	52	90	75
GPT-5 NanoOpenAI	OpenAI	53	98	51	98	75
Qwen3 8BAlibaba	Alibaba	64	95	43	98	75
Kimi K2.7 Code (batch)Moonshot AI	Moonshot AI	58	95	48	98	75
Hy3 previewTencent	Tencent	65	95	48	90	75
Step 3.5 FlashStepFun	StepFun	63	98	46	90	74
gpt-oss-20bOpenAI	OpenAI	61	98	40	98	74
gpt-oss-20b (free)OpenAI	OpenAI	61	98	40	98	74
Composer 2Cursor	Cursor	63	98	46	90	74
Composer 2 FastCursor	Cursor	63	98	46	90	74
Gemini 3.1 Flash LiteGoogle	Google	50	100	48	98	74
Gemini 3.1 Flash Lite (batch)Google	Google	50	100	48	98	74
Nano Banana Pro (Gemini 3 Pro Image)Google	Google	50	98	48	98	74
Claude Opus 5 (batch)Anthropic	Anthropic	47	100	46	98	73
Claude Sonnet 5 (batch)Anthropic	Anthropic	47	100	46	98	73
Fugu Ultrasakana	sakana	47	100	46	98	73
Claude Fable Latest~anthropic	~anthropic	47	100	46	98	73
Google Gemini Pro Latest~google	~google	47	100	46	98	73
Google Gemini Flash Latest~google	~google	47	100	46	98	73
Anthropic Claude Sonnet Latest~anthropic	~anthropic	47	100	46	98	73
OpenAI GPT Latest~openai	~openai	47	100	46	98	73
Claude Opus Latest~anthropic	~anthropic	47	100	46	98	73
Kimi K2 ThinkingMoonshot AI	Moonshot AI	58	98	37	98	73
Anthropic Claude Haiku Latest~anthropic	~anthropic	47	98	46	98	72
OpenAI GPT Mini Latest~openai	~openai	47	98	46	98	72
Qwen3 235B A22BAlibaba	Alibaba	58	95	38	98	72
Grok Latest~x-ai	~x-ai	47	95	46	98	72
Grok Build 0.1xAI	xAI	47	95	46	98	72
Qwen3 VL 8B ThinkingAlibaba	Alibaba	50	98	40	98	72
Qwen3 VL 30B A3B ThinkingAlibaba	Alibaba	50	98	40	98	72
o1-proOpenAI	OpenAI	74	98	70	43	71
o1-pro (batch)OpenAI	OpenAI	74	98	70	43	71
Qwen3.7 FlashAlibaba	Alibaba	47	100	38	98	71
Kimi K3Moonshot AI	Moonshot AI	47	100	38	98	71
MoonshotAI Kimi Latest~moonshotai	~moonshotai	47	100	38	98	71
Qwen3.6 FlashAlibaba	Alibaba	47	100	38	98	71
Step 3.7 FlashStepFun	StepFun	47	98	38	98	70
Qwen3.6 35B A3BAlibaba	Alibaba	47	98	38	98	70
Qwen3.6 27BAlibaba	Alibaba	47	98	38	98	70
Seed-2.0-LiteByteDance	ByteDance	47	98	38	98	70
Seed-2.0-MiniByteDance	ByteDance	47	98	38	98	70
Seed 1.6 FlashByteDance	ByteDance	47	98	38	98	70
Seed 1.6ByteDance	ByteDance	47	98	38	98	70
Mistral Small 4Mistral AI	Mistral AI	47	95	38	98	70
Qwen Plus 0728 (thinking)Alibaba	Alibaba	50	100	30	98	70
GPT-4o (batch)OpenAI	OpenAI	63	48	68	98	69
gpt-oss-safeguard-20bOpenAI	OpenAI	50	98	30	98	69
Qwen3 32BAlibaba	Alibaba	50	98	30	98	69
GPT-4.1OpenAI	OpenAI	59	53	65	98	69
GPT-4.1 (batch)OpenAI	OpenAI	59	53	65	98	69
DeepSeek V4 Flash Latest~deepseek	~deepseek	47	100	28	98	68
DeepSeek V4 Flash 0731DeepSeek	DeepSeek	47	100	28	98	68
DeepSeek V4 Flash 0423DeepSeek	DeepSeek	47	100	28	98	68
Nemotron 3 SuperNVIDIA	NVIDIA	47	100	28	98	68
Nemotron Nano 12B 2 VL (free)NVIDIA	NVIDIA	45	98	40	90	68
Nemotron Nano 9B V2 (free)NVIDIA	NVIDIA	50	95	30	98	68
Qwen3 14BAlibaba	Alibaba	50	95	30	98	68
Aion-3.0-Miniaion-labs	aion-labs	47	98	28	98	68
Aion-3.0aion-labs	aion-labs	47	98	28	98	68
Ring-2.6-1Tinclusionai	inclusionai	47	98	28	98	68
Nemotron 3 Super (free)NVIDIA	NVIDIA	47	98	28	98	68
Aion-2.0aion-labs	aion-labs	47	98	28	98	68
Solar Pro 3Upstage	Upstage	47	98	28	98	68
Nemotron 3 Nano 30B A3BNVIDIA	NVIDIA	47	98	28	98	68
gpt-oss-120bOpenAI	OpenAI	47	98	28	98	68
Nemotron 3 UltraNVIDIA	NVIDIA	47	95	28	98	67
Nemotron 3 Ultra (batch)NVIDIA	NVIDIA	47	95	28	98	67
Nemotron 3 Nano Omni (free)NVIDIA	NVIDIA	42	98	38	90	67
Llama 4 MaverickMeta	Meta	59	53	58	98	67
GPT-4o (2024-11-20)OpenAI	OpenAI	62	48	60	98	67
GPT-4o (2024-08-06)OpenAI	OpenAI	62	48	60	98	67
GPT-4oOpenAI	OpenAI	62	48	60	98	67
Qwen3 VL 235B A22B InstructAlibaba	Alibaba	61	48	59	98	67
GPT-4o-miniOpenAI	OpenAI	60	48	59	98	66
GPT-4o (2024-05-13)OpenAI	OpenAI	62	45	60	98	66
GPT-4o-mini (batch)OpenAI	OpenAI	55	48	62	98	66
GPT-4.1 Mini (batch)OpenAI	OpenAI	52	53	59	98	66
GPT-4.1 Nano (batch)OpenAI	OpenAI	52	53	59	98	66
Laguna S 2.1poolside	poolside	42	100	28	90	65
LongCat 2.0Meituan	Meituan	42	100	28	90	65
Nemotron 3 Ultra (free)NVIDIA	NVIDIA	42	100	28	90	65
Mistral Large 3 2512Mistral AI	Mistral AI	59	45	57	98	65
Ling 3.0 Tiny (free)inclusionai	inclusionai	42	98	28	90	65
Ling-3.0-flashinclusionai	inclusionai	42	98	28	90	65
Laguna S 2.1 (free)poolside	poolside	42	98	28	90	65
Laguna XS 2.1poolside	poolside	42	98	28	90	65
Laguna XS 2.1 (free)poolside	poolside	42	98	28	90	65
North Mini Code (free)Cohere	Cohere	42	98	28	90	65
DeepSeek V3 0324DeepSeek	DeepSeek	62	48	50	98	65
GPT-4 TurboOpenAI	OpenAI	58	45	57	98	65
GPT-4 Turbo (batch)OpenAI	OpenAI	54	45	61	98	65
DeepSeek V3DeepSeek	DeepSeek	61	48	49	98	64
Nemotron 3 Nano 30B A3B (free)NVIDIA	NVIDIA	42	95	28	90	64
GPT-4.1 MiniOpenAI	OpenAI	48	53	56	98	64
SWE-1.5Windsurf	Windsurf	45	90	30	90	64
Falcon-H1-Arabic 34B InstructTII	TII	42	95	28	90	64
Falcon-H1-Arabic 7B InstructTII	TII	42	95	28	90	64
Falcon-H1-Arabic 3B InstructTII	TII	42	95	28	90	64
Falcon Arabic 7B InstructTII	TII	45	90	30	90	64
Falcon3 10B InstructTII	TII	45	90	30	90	64
Falcon3 7B InstructTII	TII	45	90	30	90	64
Qwen3 MaxAlibaba	Alibaba	59	48	47	98	63
Qwen3 Next 80B A3B InstructAlibaba	Alibaba	59	48	47	98	63
Llama 3.3 70B InstructMeta	Meta	58	48	47	98	63
Llama 3.1 70B InstructMeta	Meta	57	48	46	98	62
Qwen3 235B A22B Instruct 2507Alibaba	Alibaba	57	48	45	98	62
Llama 4 ScoutMeta	Meta	49	53	48	98	62
Qwen3 30B A3B Instruct 2507Alibaba	Alibaba	56	48	45	98	62
Mistral Large 2407Mistral AI	Mistral AI	58	45	46	98	62
Mistral LargeMistral AI	Mistral AI	58	45	46	98	62
GPT-4o-mini (2024-07-18)OpenAI	OpenAI	50	48	50	98	62
GPT-4 Turbo PreviewOpenAI	OpenAI	57	45	45	98	61
GPT-4OpenAI	OpenAI	57	40	45	98	60
Nano Banana 2 (Gemini 3.1 Flash Image)Google	Google	50	98	48	43	60
GPT-5.4 Image 2OpenAI	OpenAI	50	98	48	43	60
GPT-5 Image MiniOpenAI	OpenAI	50	98	48	43	60
GPT-5 ImageOpenAI	OpenAI	50	98	48	43	60
Mixtral 8x22B InstructMistral AI	Mistral AI	56	40	44	98	60
GPT-4.1 NanoOpenAI	OpenAI	39	53	47	98	59
Sonar Pro SearchPerplexity	Perplexity	50	95	48	43	59
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google	Google	50	93	48	43	59
Granite 4.1 8BIBM	IBM	49	48	39	98	59
Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google	Google	50	93	48	43	59
Nano Banana Pro (Gemini 3 Pro Image Preview)Google	Google	50	93	48	43	59
Olmo 3 32B ThinkAllen AI	Allen AI	59	93	38	43	58
Kimi K2 0905Moonshot AI	Moonshot AI	47	48	37	98	58
Claude 3 HaikuAnthropic	Anthropic	41	45	54	90	58
GPT Chat LatestOpenAI	OpenAI	37	48	46	98	57
Qwen3 VL 32B InstructAlibaba	Alibaba	40	48	40	98	57
Qwen3 VL 8B InstructAlibaba	Alibaba	40	48	40	98	57
Qwen3 VL 30B A3B InstructAlibaba	Alibaba	40	48	40	98	57
Mistral Small 3.2 24BMistral AI	Mistral AI	40	48	40	98	57
Gemma 3 12BGoogle	Google	40	48	40	98	57
Gemma 3 27BGoogle	Google	40	48	40	98	57
Ministral 3 14B 2512Mistral AI	Mistral AI	40	45	40	98	56
Ministral 3 8B 2512Mistral AI	Mistral AI	40	45	40	98	56
Ministral 3 3B 2512Mistral AI	Mistral AI	40	45	40	98	56
Mistral Medium 3.1Mistral AI	Mistral AI	40	45	40	98	56
Mistral Medium 3Mistral AI	Mistral AI	40	45	40	98	56
Sonar Reasoning ProPerplexity	Perplexity	45	95	48	35	56
Qwen3 Coder PlusAlibaba	Alibaba	40	53	30	98	55
Qwen3 Coder FlashAlibaba	Alibaba	40	53	30	98	55
Qwen Plus 0728Alibaba	Alibaba	40	53	30	98	55
Hunyuan A13B InstructTencent	Tencent	50	98	30	43	55
Qwen-PlusAlibaba	Alibaba	40	53	30	98	55
Command R (08-2024)Cohere	Cohere	44	45	34	98	55
Command R+ (08-2024)Cohere	Cohere	44	45	34	98	55
Perceptron Mk1perceptron	perceptron	47	90	38	43	55
Cogito v2.1 671Bdeepcogito	deepcogito	50	95	30	43	55
Nova Premier 1.0Amazon	Amazon	35	53	40	90	55
Llama 3.1 8B InstructMeta	Meta	41	48	31	98	55
Reka Edgerekaai	rekaai	37	43	38	98	54
Qwen3 Coder 30B A3B InstructAlibaba	Alibaba	40	48	30	98	54
Qwen3 Coder 480B A35BAlibaba	Alibaba	40	48	30	98	54
Reka Flash 3rekaai	rekaai	50	93	30	43	54
Mistral NemoMistral AI	Mistral AI	40	48	30	98	54
GPT-3.5 Turbo (batch)OpenAI	OpenAI	40	40	38	98	54
Kimi K2 0711Moonshot AI	Moonshot AI	41	48	36	90	54
Jamba Large 1.7AI21 Labs	AI21 Labs	40	45	30	98	53
Codestral 2508Mistral AI	Mistral AI	40	45	30	98	53
ERNIE 4.5 VL 424B A47B Baidu	Baidu	45	93	40	35	53
Sonar Deep ResearchPerplexity	Perplexity	45	95	38	35	53
KAT-Coder-Air V2.5Kuaishou	Kuaishou	37	48	28	98	53
KAT-Coder-Pro V2.5Kuaishou	Kuaishou	37	48	28	98	53
Ling-2.6-1Tinclusionai	inclusionai	37	48	28	98	53
Ling-2.6-flashinclusionai	inclusionai	37	48	28	98	53
KAT-Coder-Pro V2Kuaishou	Kuaishou	37	48	28	98	53
Qwen3 Coder NextAlibaba	Alibaba	37	48	28	98	53
GPT AudioOpenAI	OpenAI	37	48	28	98	53
GPT Audio MiniOpenAI	OpenAI	37	48	28	98	53
Qwen2.5 7B InstructAlibaba	Alibaba	40	43	30	98	53
Qwen2.5 72B InstructAlibaba	Alibaba	40	43	30	98	53
Nemotron 3.5 Content Safety (free)NVIDIA	NVIDIA	42	95	38	35	53
Nova Lite 1.0Amazon	Amazon	35	45	40	90	53
Nova Pro 1.0Amazon	Amazon	35	45	40	90	53
Voxtral Small 24B 2507Mistral AI	Mistral AI	40	40	30	98	52
SabaMistral AI	Mistral AI	40	40	30	98	52
GPT-3.5 Turbo (older v0613)OpenAI	OpenAI	40	40	30	98	52
GPT-3.5 Turbo 16kOpenAI	OpenAI	40	40	30	98	52
GPT-3.5 TurboOpenAI	OpenAI	40	40	30	98	52
Gemma 2 27BGoogle	Google	67	40	54	43	51
Virtuoso Largearcee-ai	arcee-ai	35	48	30	90	51
Nova Micro 1.0Amazon	Amazon	35	45	30	90	50
R1 Distill Llama 70BDeepSeek	DeepSeek	43	90	28	35	49
Phi 4Microsoft	Microsoft	53	43	42	43	45
MiniMax M2-herMiniMax	MiniMax	55	40	48	35	45
Llama Guard 4 12BMeta	Meta	40	53	40	43	44
Lyria 3 Pro PreviewGoogle	Google	37	53	38	43	43
Lyria 3 Clip PreviewGoogle	Google	37	53	38	43	43
Nano Banana (Gemini 2.5 Flash Image)Google	Google	40	40	48	43	43
Gemma 3 4BGoogle	Google	40	48	40	43	43
Command ACohere	Cohere	46	45	36	43	43
UI-TARS 7B ByteDance	ByteDance	40	45	40	43	42
Qwen2.5 VL 72B InstructAlibaba	Alibaba	40	45	40	43	42
Sonar ProPerplexity	Perplexity	35	45	48	35	41
MiniMax-01MiniMax	MiniMax	35	53	40	35	41
Granite 4.0 MicroIBM	IBM	40	48	30	43	40
Llama 3.2 3B InstructMeta	Meta	40	48	30	43	40
Mistral Small 3.1 24BMistral AI	Mistral AI	35	48	40	35	40
SonarPerplexity	Perplexity	35	40	48	35	40
Command R7B (12-2024)Cohere	Cohere	40	45	30	43	40
Mistral Small 3Mistral AI	Mistral AI	40	43	30	43	39
Gemma 3n 4BGoogle	Google	40	40	30	43	38
WizardLM-2 8x22BMicrosoft	Microsoft	40	40	30	43	38
GPT-3.5 Turbo InstructOpenAI	OpenAI	40	40	30	43	38
Palmyra X5Writer	Writer	32	50	28	35	36
Qwen2.5 Coder 32B InstructAlibaba	Alibaba	35	43	30	35	36
Llama 3.2 1B InstructMeta	Meta	35	43	30	35	36
autofixer-01Vercel	Vercel	35	40	30	35	35
MellumJetBrains	JetBrains	35	40	30	35	35
ALLaM 7B Instruct (preview)HUMAIN	HUMAIN	35	40	30	35	35
ALLaM 1 13B InstructHUMAIN	HUMAIN	35	40	30	35	35
ALLaM 2 7B InstructHUMAIN	HUMAIN	35	40	30	35	35
ALLaM 34BHUMAIN	HUMAIN	35	40	30	35	35
Falcon Mamba 7B InstructTII	TII	35	40	30	35	35
Midjourney v6.1Midjourney	Midjourney	35	40	30	30	34
DALL-E 3OpenAI	OpenAI	35	40	30	30	34
Stable Diffusion 3.5Stability AI	Stability AI	35	40	30	30	34
FLUX.1 ProBlack Forest Labs	Black Forest Labs	35	40	30	30	34
Ideogram 2.0Ideogram	Ideogram	35	40	30	30	34
Recraft V3Recraft	Recraft	35	40	30	30	34
Imagen 3Google	Google	35	40	30	30	34
Adobe Firefly 3Adobe	Adobe	35	40	30	30	34
Leonardo PhoenixLeonardo AI	Leonardo AI	35	40	30	30	34
SoraOpenAI	OpenAI	35	40	30	30	34
Veo 2Google	Google	35	40	30	30	34
Runway Gen-3 AlphaRunway	Runway	35	40	30	30	34
Kling 1.6Kuaishou	Kuaishou	35	40	30	30	34
Pika 2.0Pika	Pika	35	40	30	30	34
MiniMax Video-01MiniMax	MiniMax	35	40	30	30	34
Luma Dream MachineLuma AI	Luma AI	35	40	30	30	34
Stable Video DiffusionStability AI	Stability AI	35	40	30	30	34
Wan 2.1 T2VWan AI	Wan AI	35	40	30	30	34
LTX-Video 2Lightricks	Lightricks	35	40	30	30	34

Explore More

Dive deeper with capability filters, pricing comparisons, or the full leaderboard.

All Explorers Capabilities Benchmarks Overview Leaderboard Compare Models

Frequently Asked Questions

AI benchmarks are standardized tests that measure model performance on specific tasks - math (MATH-500), coding (HumanEval, SWE-bench), reasoning (GPQA), knowledge (MMLU), and conversational ability (Arena ELO). They help compare models objectively.

No single benchmark tells the full story. Arena ELO (crowdsourced human preferences) best reflects real-world quality. SWE-bench is most relevant for coding. MATH-500 and GPQA test reasoning depth. Use multiple benchmarks for evaluation.

Benchmarks have limitations - models can be trained on benchmark data (contamination), and high scores don't always predict real-world performance. Arena ELO is hardest to game since it uses blind human comparisons. Use benchmarks as one signal among many.