Benchmark Explorer

Compare 367 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

367

With Reasoning

197

With Vision

163

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	GPT-5.4 ProOpenAI	OpenAI	100
2	GPT-5.4OpenAI	OpenAI	100
3	Claude Opus 4.6 (Fast)Anthropic	Anthropic	100
4	Claude Opus 4.6Anthropic	Anthropic	100
5	Grok 4.20xAI	xAI	100
6	Gemini 3 Flash PreviewGoogle	Google	100
7	Claude Sonnet 4.6Anthropic	Anthropic	100
8	Gemini 2.5 ProGoogle	Google	100
9	Gemini 2.5 Pro Preview 06-05Google	Google	100
10	Gemini 2.5 Pro Preview 05-06Google	Google	100
11	Claude Sonnet 4.5Anthropic	Anthropic	100
12	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	100
13	Gemini 3.1 Pro PreviewGoogle	Google	100
14	Gemini 3.1 Flash Lite PreviewGoogle	Google	100
15	Claude Opus 4.7Anthropic	Anthropic	100

Code Generation

Code writing, debugging, and software engineering tasks.

#	Model	Provider	Score
1	GPT-5.4 ProOpenAI	OpenAI	89
2	GPT-5.4OpenAI	OpenAI	89
3	Claude Opus 4.6 (Fast)Anthropic	Anthropic	87
4	Claude Opus 4.6Anthropic	Anthropic	87
5	GPT-5.2 ProOpenAI	OpenAI	87
6	GPT-5.2-CodexOpenAI	OpenAI	87
7	GPT-5.2OpenAI	OpenAI	87
8	Grok 4.20xAI	xAI	86
9	Gemini 3 Flash PreviewGoogle	Google	86
10	GPT-5.3-CodexOpenAI	OpenAI	86
11	GPT-5 ProOpenAI	OpenAI	86
12	GPT-5.1-Codex-MaxOpenAI	OpenAI	85
13	Grok 4xAI	xAI	85
14	GPT-5.1OpenAI	OpenAI	85
15	GPT-5.1-CodexOpenAI	OpenAI	85

Language Understanding

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

#	Model	Provider	Score
1	GPT-5.4 ProOpenAI	OpenAI	82
2	GPT-5.4OpenAI	OpenAI	82
3	Claude Opus 4.6 (Fast)Anthropic	Anthropic	81
4	Claude Opus 4.6Anthropic	Anthropic	81
5	GPT-5.2 ProOpenAI	OpenAI	81
6	Grok 4.20xAI	xAI	80
7	Gemini 3 Flash PreviewGoogle	Google	80
8	GPT-5.3-CodexOpenAI	OpenAI	80
9	GPT-5 ProOpenAI	OpenAI	80
10	Grok 4xAI	xAI	80
11	Grok 4.20 Multi-AgentxAI	xAI	80
12	GPT-5.1-Codex-MaxOpenAI	OpenAI	79
13	o3 Deep ResearchOpenAI	OpenAI	79
14	o3 ProOpenAI	OpenAI	79
15	o3OpenAI	OpenAI	79

Tool Use

Function calling, structured output, and agentic workflows.

#	Model	Provider	Score
1	GPT-5.4 ProOpenAI	OpenAI	98
2	GPT-5.4OpenAI	OpenAI	98
3	Claude Opus 4.6 (Fast)Anthropic	Anthropic	98
4	Claude Opus 4.6Anthropic	Anthropic	98
5	Grok 4.20xAI	xAI	98
6	Gemini 3 Flash PreviewGoogle	Google	98
7	GPT-5.2 ProOpenAI	OpenAI	98
8	GPT-5.3-CodexOpenAI	OpenAI	98
9	GPT-5 ProOpenAI	OpenAI	98
10	GPT-5.1-Codex-MaxOpenAI	OpenAI	98
11	Claude Sonnet 4.6Anthropic	Anthropic	98
12	o3 Deep ResearchOpenAI	OpenAI	98
13	o3 ProOpenAI	OpenAI	98
14	o3OpenAI	OpenAI	98
15	Grok 4xAI	xAI	98

Cross-Benchmark Comparison

All 367 models ranked by average score across all four benchmark categories.

Model	Provider	Code	Reasoning	Language	Tool Use	Average
GPT-5.4 ProOpenAI	OpenAI	89	100	82	98	92
GPT-5.4OpenAI	OpenAI	89	100	82	98	92
Claude Opus 4.6 (Fast)Anthropic	Anthropic	87	100	81	98	92
Claude Opus 4.6Anthropic	Anthropic	87	100	81	98	92
Grok 4.20xAI	xAI	86	100	80	98	91
Gemini 3 Flash PreviewGoogle	Google	86	100	80	98	91
GPT-5.2 ProOpenAI	OpenAI	87	98	81	98	91
GPT-5.3-CodexOpenAI	OpenAI	86	98	80	98	91
GPT-5 ProOpenAI	OpenAI	86	98	80	98	91
GPT-5.1-Codex-MaxOpenAI	OpenAI	85	98	79	98	90
Claude Sonnet 4.6Anthropic	Anthropic	83	100	78	98	90
o3 Deep ResearchOpenAI	OpenAI	84	98	79	98	90
o3 ProOpenAI	OpenAI	84	98	79	98	90
o3OpenAI	OpenAI	84	98	79	98	90
Grok 4xAI	xAI	85	95	80	98	90
Claude Opus 4.5Anthropic	Anthropic	83	98	78	98	89
GPT-5.2-CodexOpenAI	OpenAI	87	98	73	98	89
GPT-5.2OpenAI	OpenAI	87	98	73	98	89
Gemini 2.5 ProGoogle	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
Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	80	100	75	98	88
Gemini 3.1 Pro PreviewGoogle	Google	80	100	75	98	88
GPT-5.1OpenAI	OpenAI	85	98	71	98	88
GPT-5.1-CodexOpenAI	OpenAI	85	98	71	98	88
GPT-5.1-Codex-MiniOpenAI	OpenAI	85	98	71	98	88
GPT-5 CodexOpenAI	OpenAI	85	98	71	98	88
GPT-5OpenAI	OpenAI	85	98	71	98	88
Gemini 3.1 Flash Lite PreviewGoogle	Google	79	100	74	98	88
o4 Mini Deep ResearchOpenAI	OpenAI	80	98	75	98	88
o4 MiniOpenAI	OpenAI	80	98	75	98	88
Claude Opus 4.7Anthropic	Anthropic	78	100	74	98	88
GPT-5.5 ProOpenAI	OpenAI	78	100	73	98	87
GPT-5.5OpenAI	OpenAI	78	100	73	98	87
Gemini 2.5 Flash Lite Preview 09-2025Google	Google	78	100	73	98	87
Gemini 2.5 Flash LiteGoogle	Google	78	100	73	98	87
Gemini 2.5 FlashGoogle	Google	78	100	73	98	87
GPT-5.4 NanoOpenAI	OpenAI	78	98	74	98	87
GPT-5.4 MiniOpenAI	OpenAI	78	98	74	98	87
Grok 4.1 FastxAI	xAI	77	100	73	98	87
Grok 4.3xAI	xAI	76	100	71	98	86
Claude Opus 4.1Anthropic	Anthropic	75	98	71	98	86
Gemma 4 31B (free)Google	Google	79	98	66	98	85
Gemma 4 31BGoogle	Google	79	98	66	98	85
Qwen3.5 397B A17BAlibaba	Alibaba	79	98	66	98	85
Grok 4 FastxAI	xAI	73	100	69	98	85
Claude Opus 4Anthropic	Anthropic	76	98	75	90	85
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
Kimi K2.6Moonshot AI	Moonshot AI	76	98	63	98	84
Qwen3.6 PlusAlibaba	Alibaba	75	100	62	98	84
Qwen3.5-35B-A3BAlibaba	Alibaba	76	98	63	98	84
Claude Haiku 4.5Anthropic	Anthropic	71	98	67	98	84
o1OpenAI	OpenAI	74	98	62	98	83
R1 0528DeepSeek	DeepSeek	79	98	56	98	83
MiMo-V2.5Xiaomi	Xiaomi	72	100	60	98	83
Gemma 4 26B A4B (free)Google	Google	73	98	61	98	83
Claude Sonnet 4Anthropic	Anthropic	70	100	70	90	83
MiniMax M2.5MiniMax	MiniMax	78	98	55	98	82
Claude 3.7 Sonnet (thinking)Anthropic	Anthropic	70	98	70	90	82
DeepSeek V4 ProDeepSeek	DeepSeek	76	100	53	98	82
MiMo-V2.5-ProXiaomi	Xiaomi	76	100	53	98	82
Gemma 4 26B A4B Google	Google	73	95	61	98	82
Qwen3.5-FlashAlibaba	Alibaba	70	100	58	98	82
MiniMax M2.5 (free)MiniMax	MiniMax	78	95	55	98	82
GLM 5.1Zhipu AI	Zhipu AI	76	98	53	98	81
GLM 5Zhipu AI	Zhipu AI	77	95	55	98	81
GPT-5 MiniOpenAI	OpenAI	66	98	63	98	81
Claude 3.7 SonnetAnthropic	Anthropic	68	98	69	90	81
MiMo-V2-ProXiaomi	Xiaomi	74	100	52	98	81
GLM 4.5Zhipu AI	Zhipu AI	75	98	53	98	81
Qwen3.6 Max PreviewAlibaba	Alibaba	75	98	52	98	81
o3 MiniOpenAI	OpenAI	75	98	52	98	81
Qwen3 VL 235B A22B ThinkingAlibaba	Alibaba	69	98	57	98	81
DeepSeek V4 FlashDeepSeek	DeepSeek	73	100	50	98	80
Qwen3.5-9BAlibaba	Alibaba	68	98	57	98	80
GLM 4.7Zhipu AI	Zhipu AI	73	98	51	98	80
MiniMax M2MiniMax	MiniMax	73	98	50	98	80
GLM 5 TurboZhipu AI	Zhipu AI	72	98	50	98	80
GLM 4.6Zhipu AI	Zhipu AI	72	98	49	98	79
MiniMax M2.1MiniMax	MiniMax	71	98	49	98	79
DeepSeek V3.2DeepSeek	DeepSeek	71	98	49	98	79
DeepSeek V3.2 ExpDeepSeek	DeepSeek	71	98	49	98	79
DeepSeek V3.1 TerminusDeepSeek	DeepSeek	71	98	49	98	79
MiniMax M2.7MiniMax	MiniMax	70	98	48	98	79
Qwen3 Max ThinkingAlibaba	Alibaba	70	98	48	98	79
Step 3.5 FlashStepFun	StepFun	68	98	47	98	78
Grok 3 Mini BetaxAI	xAI	65	95	52	98	78
Trinity Large Thinkingarcee-ai	arcee-ai	67	98	46	98	77
Kimi K2.5Moonshot AI	Moonshot AI	62	98	51	98	77
Grok 4.20 Multi-AgentxAI	xAI	85	100	80	43	77
GLM 4.7 FlashZhipu AI	Zhipu AI	66	98	45	98	77
Qwen3 Next 80B A3B ThinkingAlibaba	Alibaba	66	98	45	98	77
Qwen3 30B A3B Thinking 2507Alibaba	Alibaba	66	98	45	98	77
MiniMax M1MiniMax	MiniMax	67	100	50	90	77
DeepSeek V3.1DeepSeek	DeepSeek	70	90	48	98	77
Qwen3 235B A22B Thinking 2507Alibaba	Alibaba	67	95	46	98	77
GLM 4.6VZhipu AI	Zhipu AI	62	98	55	90	76
o3 Mini HighOpenAI	OpenAI	65	98	44	98	76
GLM 4.5 Air (free)Zhipu AI	Zhipu AI	67	98	49	90	76
GLM 4.5 AirZhipu AI	Zhipu AI	67	98	49	90	76
Mercury 2Inception	Inception	64	98	43	98	76
Qwen3 30B A3BAlibaba	Alibaba	66	93	45	98	76
R1DeepSeek	DeepSeek	68	93	51	90	76
Hy3 previewTencent	Tencent	65	98	48	90	75
Llama 3.3 Nemotron Super 49B V1.5NVIDIA	NVIDIA	63	98	42	98	75
GPT-5.3 ChatOpenAI	OpenAI	75	48	79	98	75
Nova 2 LiteAmazon	Amazon	58	100	52	90	75
GPT-5.1 ChatOpenAI	OpenAI	74	48	79	98	75
gpt-oss-20bOpenAI	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
GLM 4.5VZhipu AI	Zhipu AI	59	93	53	90	74
Qwen3 8BAlibaba	Alibaba	63	90	42	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
Grok 3 MinixAI	xAI	55	95	43	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
GPT-5 NanoOpenAI	OpenAI	52	95	42	98	72
Qwen3.5 Plus 2026-04-20Alibaba	Alibaba	47	100	38	98	71
Qwen3.6 FlashAlibaba	Alibaba	47	100	38	98	71
Qwen3.5 Plus 2026-02-15Alibaba	Alibaba	47	100	38	98	71
MoonshotAI Kimi Latest~moonshotai	~moonshotai	47	98	38	98	70
Qwen3.6 35B A3BAlibaba	Alibaba	47	98	38	98	70
Qwen3.6 27BAlibaba	Alibaba	47	98	38	98	70
GLM 5V TurboZhipu AI	Zhipu AI	47	98	38	98	70
MiMo-V2-OmniXiaomi	Xiaomi	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
Qwen3 VL 8B ThinkingAlibaba	Alibaba	47	98	38	98	70
Qwen3 VL 30B A3B ThinkingAlibaba	Alibaba	47	98	38	98	70
gpt-oss-20b (free)OpenAI	OpenAI	55	95	40	90	70
Gemini 2.0 FlashGoogle	Google	63	50	69	98	70
Mistral Medium 3.5Mistral AI	Mistral AI	47	95	38	98	70
Mistral Small 4Mistral AI	Mistral AI	47	95	38	98	70
GPT-5.2 ChatOpenAI	OpenAI	66	48	64	98	69
Grok Code Fast 1xAI	xAI	47	95	36	98	69
o1-proOpenAI	OpenAI	73	98	61	43	69
Qwen Plus 0728 (thinking)Alibaba	Alibaba	47	100	28	98	68
Nemotron 3 Super (free)NVIDIA	NVIDIA	47	98	28	98	68
MiMo-V2-FlashXiaomi	Xiaomi	47	98	28	98	68
Nemotron 3 Nano 30B A3BNVIDIA	NVIDIA	47	98	28	98	68
Trinity Miniarcee-ai	arcee-ai	47	98	28	98	68
gpt-oss-safeguard-20bOpenAI	OpenAI	47	98	28	98	68
Tongyi DeepResearch 30B A3BAlibaba	Alibaba	47	98	28	98	68
Nemotron Nano 9B V2NVIDIA	NVIDIA	47	98	28	98	68
Nemotron 3 Nano Omni (free)NVIDIA	NVIDIA	42	98	38	90	67
Nemotron 3 SuperNVIDIA	NVIDIA	47	95	28	98	67
Solar Pro 3Upstage	Upstage	47	95	28	98	67
Nemotron Nano 12B 2 VL (free)NVIDIA	NVIDIA	42	98	38	90	67
Nemotron Nano 9B V2 (free)NVIDIA	NVIDIA	47	95	28	98	67
gpt-oss-120bOpenAI	OpenAI	47	95	28	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
Grok 3xAI	xAI	64	45	59	98	67
Qwen3 14BAlibaba	Alibaba	47	93	28	98	67
Qwen3 32BAlibaba	Alibaba	47	93	28	98	67
Grok 3 BetaxAI	xAI	64	45	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-4.1OpenAI	OpenAI	59	50	57	98	66
gpt-oss-120b (free)OpenAI	OpenAI	45	98	30	90	66
ERNIE 4.5 VL 28B A3BBaidu	Baidu	42	90	38	90	65
Falcon-H1-Arabic 34B InstructTII	TII	45	95	30	90	65
Falcon-H1-Arabic 7B InstructTII	TII	45	95	30	90	65
Falcon-H1-Arabic 3B InstructTII	TII	45	95	30	90	65
Mistral Large 3 2512Mistral AI	Mistral AI	59	45	57	98	65
Gemini 2.0 Flash LiteGoogle	Google	52	50	59	98	65
Ring-2.6-1T (free)inclusionai	inclusionai	42	98	28	90	65
CoBuddy (free)Baidu	Baidu	42	98	28	90	65
DeepSeek V3 0324DeepSeek	DeepSeek	62	48	50	98	65
GPT-4 TurboOpenAI	OpenAI	58	45	57	98	65
GPT-4o AudioOpenAI	OpenAI	61	48	49	98	64
DeepSeek V3DeepSeek	DeepSeek	61	48	49	98	64
Laguna XS.2 (free)poolside	poolside	42	95	28	90	64
Laguna M.1 (free)poolside	poolside	42	95	28	90	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 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
Qwen3 Next 80B A3B Instruct (free)Alibaba	Alibaba	59	45	47	98	62
Llama 3.1 70B InstructMeta	Meta	57	48	46	98	62
Qwen3 235B A22B Instruct 2507Alibaba	Alibaba	57	48	45	98	62
Mistral LargeMistral AI	Mistral AI	58	45	46	98	62
GPT-4o-mini (2024-07-18)OpenAI	OpenAI	50	48	49	98	61
Trinity Large Previewarcee-ai	arcee-ai	56	45	45	98	61
Llama 4 ScoutMeta	Meta	48	48	48	98	61
Claude 3.5 HaikuAnthropic	Anthropic	47	45	59	90	60
GPT-4o (2024-11-20)OpenAI	OpenAI	47	48	47	98	60
GPT-4 (older v0314)OpenAI	OpenAI	57	40	45	98	60
GPT-4OpenAI	OpenAI	57	40	45	98	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 Turbo PreviewOpenAI	OpenAI	53	45	42	98	60
GPT-4 Turbo (older v1106)OpenAI	OpenAI	53	45	42	98	60
GPT-4.1 NanoOpenAI	OpenAI	39	53	47	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
Mistral Large 2407Mistral AI	Mistral AI	50	45	39	98	58
Sonar Pro SearchPerplexity	Perplexity	47	95	46	43	58
Kimi K2 0905Moonshot AI	Moonshot AI	47	48	37	98	58
GPT Chat LatestOpenAI	OpenAI	37	48	46	98	57
Llama 3.3 70B Instruct (free)Meta	Meta	53	40	46	90	57
Mistral Medium 3Mistral AI	Mistral AI	40	45	40	98	56
Pixtral Large 2411Mistral AI	Mistral AI	40	45	40	98	56
Qwen3 VL 32B InstructAlibaba	Alibaba	37	48	38	98	55
Qwen3 VL 8B InstructAlibaba	Alibaba	37	48	38	98	55
Qwen3 VL 30B A3B InstructAlibaba	Alibaba	37	48	38	98	55
Mistral Small 3.2 24BMistral AI	Mistral AI	37	48	38	98	55
Gemma 3 12BGoogle	Google	37	48	38	98	55
Gemma 3 27BGoogle	Google	37	48	38	98	55
Qwen VL MaxAlibaba	Alibaba	37	48	38	98	55
Command R+ (08-2024)Cohere	Cohere	44	45	34	98	55
Command R (08-2024)Cohere	Cohere	44	45	34	98	55
R1 Distill Llama 70BDeepSeek	DeepSeek	49	98	30	43	55
Claude 3 HaikuAnthropic	Anthropic	40	45	45	90	55
GPT-5 ChatOpenAI	OpenAI	61	48	67	43	55
Devstral Small 1.1Mistral AI	Mistral AI	43	45	33	98	55
Ministral 3 14B 2512Mistral AI	Mistral AI	37	45	38	98	55
Ministral 3 8B 2512Mistral AI	Mistral AI	37	45	38	98	55
Ministral 3 3B 2512Mistral AI	Mistral AI	37	45	38	98	55
Mistral Medium 3.1Mistral AI	Mistral AI	37	45	38	98	55
Sonar Reasoning ProPerplexity	Perplexity	42	95	46	35	55
Reka Edgerekaai	rekaai	37	43	38	98	54
Devstral 2 2512Mistral AI	Mistral AI	41	45	32	98	54
DeepSeek V3.2 SpecialeDeepSeek	DeepSeek	47	98	28	43	54
Qwen3 Coder PlusAlibaba	Alibaba	37	53	28	98	54
Qwen3 Coder FlashAlibaba	Alibaba	37	53	28	98	54
Qwen Plus 0728Alibaba	Alibaba	37	53	28	98	54
Devstral MediumMistral AI	Mistral AI	41	45	32	98	54
Hunyuan A13B InstructTencent	Tencent	47	98	28	43	54
Qwen-PlusAlibaba	Alibaba	37	53	28	98	54
R1 Distill Qwen 32BDeepSeek	DeepSeek	50	93	30	43	54
Kimi K2 0711Moonshot AI	Moonshot AI	41	48	36	90	54
Cogito v2.1 671Bdeepcogito	deepcogito	47	95	28	43	53
Nova Premier 1.0Amazon	Amazon	32	53	38	90	53
Mistral Large 2411Mistral AI	Mistral AI	40	45	30	98	53
Mistral NemoMistral AI	Mistral AI	40	45	30	98	53
Llama 4 MaverickMeta	Meta	59	53	57	43	53
Llama 3.1 8B InstructMeta	Meta	40	43	31	98	53
Granite 4.1 8BIBM	IBM	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
Qwen3 Coder 30B A3B InstructAlibaba	Alibaba	37	48	28	98	53
Qwen3 30B A3B Instruct 2507Alibaba	Alibaba	37	48	28	98	53
Qwen3 Coder 480B A35BAlibaba	Alibaba	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
Nova Pro 1.0Amazon	Amazon	35	45	40	90	53
GPT-4o Search PreviewOpenAI	OpenAI	61	48	57	43	52
Qianfan-OCR-Fast (free)Baidu	Baidu	42	93	38	35	52
Voxtral Small 24B 2507Mistral AI	Mistral AI	40	40	30	98	52
Jamba Large 1.7AI21 Labs	AI21 Labs	37	45	28	98	52
Codestral 2508Mistral AI	Mistral AI	37	45	28	98	52
ERNIE 4.5 VL 424B A47B Baidu	Baidu	42	93	38	35	52
Sonar Deep ResearchPerplexity	Perplexity	42	95	36	35	52
Qwen-TurboAlibaba	Alibaba	37	45	28	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
Nova Lite 1.0Amazon	Amazon	32	45	38	90	51
Gemma 2 27BGoogle	Google	67	40	54	43	51
Aion-2.0aion-labs	aion-labs	42	98	28	35	51
Rnj 1 Instructessentialai	essentialai	37	40	28	98	51
ERNIE 4.5 21B A3B ThinkingBaidu	Baidu	42	98	28	35	51
SabaMistral AI	Mistral AI	37	40	28	98	51
Aion-1.0aion-labs	aion-labs	42	98	28	35	51
Aion-1.0-Miniaion-labs	aion-labs	42	98	28	35	51
Qwen-Max Alibaba	Alibaba	37	40	28	98	51
GLM 4 32B Zhipu AI	Zhipu AI	35	45	30	90	50
Qwen3 Coder 480B A35B (free)Alibaba	Alibaba	32	48	28	90	50
Virtuoso Largearcee-ai	arcee-ai	32	48	28	90	50
Reka Flash 3rekaai	rekaai	42	93	28	35	50
GPT-4o-mini Search PreviewOpenAI	OpenAI	54	48	51	43	49
LFM2.5-1.2B-Thinking (free)Liquid AI	Liquid AI	42	90	28	35	49
Nova Micro 1.0Amazon	Amazon	32	45	28	90	49
ERNIE 4.5 21B A3BBaidu	Baidu	32	40	28	90	48
Phi 4Microsoft	Microsoft	53	43	42	43	45
MiniMax M2-herMiniMax	MiniMax	55	40	48	35	45
Phi 4 Mini InstructMicrosoft	Microsoft	47	48	37	43	44
Nano Banana (Gemini 2.5 Flash Image)Google	Google	40	43	48	43	44
Lyria 3 Pro PreviewGoogle	Google	37	53	38	43	43
Lyria 3 Clip PreviewGoogle	Google	37	53	38	43	43
Llama 3.2 11B Vision InstructMeta	Meta	40	48	40	43	43
Command ACohere	Cohere	46	45	36	43	43
Llama Guard 4 12BMeta	Meta	37	48	38	43	42
Gemma 3 4BGoogle	Google	37	48	38	43	42
ERNIE 4.5 300B A47B Baidu	Baidu	48	40	42	35	41
Qwen VL PlusAlibaba	Alibaba	37	45	38	43	41
Llama 3 70B InstructMeta	Meta	46	40	40	35	40
Sonar ProPerplexity	Perplexity	32	45	46	35	40
Qwen2.5 VL 72B InstructAlibaba	Alibaba	37	40	38	43	40
MiniMax-01MiniMax	MiniMax	32	53	38	35	40
Command R7B (12-2024)Cohere	Cohere	40	45	30	43	40
Spotlightarcee-ai	arcee-ai	32	48	38	35	38
SonarPerplexity	Perplexity	32	40	46	35	38
GPT-3.5 Turbo InstructOpenAI	OpenAI	40	40	30	43	38
Mistral Small 3Mistral AI	Mistral AI	37	43	28	43	38
UI-TARS 7B ByteDance	ByteDance	32	45	38	35	38
Mistral Small 3.1 24BMistral AI	Mistral AI	32	45	38	35	38
Maestro Reasoningarcee-ai	arcee-ai	35	48	30	35	37
Palmyra X5Writer	Writer	32	50	28	35	36
Llama 3.2 3B Instruct (free)Meta	Meta	35	45	30	35	36
Granite 4.0 MicroIBM	IBM	32	45	28	35	35
Llama Guard 3 8BMeta	Meta	32	45	28	35	35
Qwen2.5 Coder 32B InstructAlibaba	Alibaba	35	40	30	35	35
Inflection 3 ProductivityInflection	Inflection	35	40	30	35	35
Inflection 3 PiInflection	Inflection	35	40	30	35	35
Llama 3.2 3B InstructMeta	Meta	35	40	30	35	35
Llama 3.2 1B InstructMeta	Meta	35	40	30	35	35
Llama 3 8B InstructMeta	Meta	35	40	30	35	35
WizardLM-2 8x22BMicrosoft	Microsoft	35	40	30	35	35
Mistral 7B Instruct v0.1Mistral AI	Mistral AI	35	40	30	35	35
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
LFM2-24B-A2BLiquid AI	Liquid AI	32	40	28	35	34
LFM2.5-1.2B-Instruct (free)Liquid AI	Liquid AI	32	40	28	35	34
Gemma 3n 4BGoogle	Google	32	40	28	35	34
Coder Largearcee-ai	arcee-ai	32	40	28	35	34
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.