LLM Leaderboard - Comparison of over 100 AI models from OpenAI, Google, DeepSeek & others

Comparison and ranking the performance of over 100 AI models (LLMs) across key metrics including intelligence, price, performance and speed (output speed - tokens per second & latency - TTFT), context window & others.

For more details including relating to our methodology, see our FAQs.

Intelligence

Updated

Claude Fable 5 (with fallback) and Claude Opus 4.8 (max) are the highest intelligence models, followed by GPT-5.5 (xhigh) and Claude Opus 4.7 (max).

Output Speed

Mercury 2 and LFM2.5-1.2B-Instruct are the fastest models, followed by LFM2 1.2B and LFM2.5-VL-1.6B.

Latency

North Mini Code and Command A+ are the lowest latency models, followed by NVIDIA Nemotron 3 Nano and NVIDIA Nemotron Nano 12B v2 VL.

Price

Qwen3.5 0.8B and Qwen3.5 0.8B are the cheapest models, followed by Gemma 3n E4B and Nova Micro.

Context Window

Llama 4 Scout and Grok 4.20 0309 support the largest context windows, followed by Gemini 1.5 Pro (May) and Grok 4.1 Fast.

Reasoning model


								Further Analysis
Claude Fable 5 (with fallback)	1M	Anthropic	60	$7.70	--	--	--	Model Providers
Claude Opus 4.8 (max)	1M	Anthropic	56	$3.85	59	18.64	27.09	Model Providers
GPT-5.5 (xhigh)	922k	OpenAI	55	$4.35	63	51.97	59.95	Model Providers
Claude Opus 4.7 (max)	1M	Anthropic	54	$3.85	51	21.81	31.52	Model Providers
GPT-5.5 (high)	922k	OpenAI	53	$4.35	58	24.46	33.06	Model Providers
GLM-5.2 (max)	1M	Z AI	51	$0.90	96	1.72	27.84	Model Providers
Gemini 3.5 Flash	1M	Google	50	$1.31	161	19.92	23.01	Model Providers
Claude Sonnet 4.6 (max)	1M	Anthropic	47	$2.31	53	102.27	111.77	Model Providers
GPT-5.5 (medium)	922k	OpenAI	47*	$4.35	60	7.86	16.20	Model Providers
Gemini 3.1 Pro Preview	1M	Google	46	$1.74	123	27.87	31.93	Model Providers
Qwen3.7 Max	1M	Alibaba	46	$1.43	112	2.65	28.60	Model Providers
Gemini 3.5 Flash (medium)	1M	Google	45*	$1.31	161	18.56	21.67	Model Providers
MiniMax-M3	1M	MiniMax	44	$0.22	62	2.89	43.27	Model Providers
DeepSeek V4 Pro (Max)	1M	DeepSeek	44	$0.18	85	1.73	58.98	Model Providers
GPT-5.3 Codex (xhigh)	400k	OpenAI	44*	$1.87	75	82.70	89.36	Model Providers
Muse Spark	262k	Meta	43	--	--	--	--	Model Providers
Kimi K2.6	256k	Kimi	43	$0.70	44	2.31	116.07	Model Providers
Claude Opus 4.7 (Non-reasoning, high)	1M	Anthropic	43*	$3.85	48	1.10	11.50	Model Providers
MiMo-V2.5-Pro	1M	Xiaomi	42	$0.18	53	2.55	49.81	Model Providers
Kimi K2.7 Code	256k	Kimi	42	$0.70	59	2.23	48.32	Model Providers
GPT-5.5 (low)	922k	OpenAI	42*	$4.35	60	1.70	10.10	Model Providers
DeepSeek V4 Pro (High)	1M	DeepSeek	41*	$0.18	81	1.78	32.65	Model Providers
DeepSeek V4 Flash (Max)	1M	DeepSeek	40	$0.06	109	1.38	57.42	Model Providers
GLM-5.1	200k	Z AI	40	$0.90	84	1.52	52.87	Model Providers
MiMo-V2.5	1M	Xiaomi	40*	$0.06	81	2.50	33.46	Model Providers
GPT-5.4 mini (xhigh)	400k	OpenAI	40	$0.65	174	6.96	9.84	Model Providers
Qwen3.6 Plus	1M	Alibaba	40	$0.43	53	2.76	117.99	Model Providers
Qwen3.7 Plus	1M	Alibaba	39	$0.25	52	2.73	50.81	Model Providers
GPT-5.4 nano (xhigh)	400k	OpenAI	38	$0.18	157	6.63	9.82	Model Providers
MiniMax-M2.7	205k	MiniMax	38	$0.22	47	2.20	64.76	Model Providers
GLM-5-Turbo	200k	Z AI	38*	--	--	--	--	Model Providers
Nemotron 3 Ultra	262k	NVIDIA	38	$0.58	172	1.14	17.28	Model Providers
Grok 4.3 (high)	1M	xAI	38	$0.64	138	11.58	15.19	Model Providers
DeepSeek V4 Flash (High)	1M	DeepSeek	37*	$0.08	--	--	--	Model Providers
Qwen3.6 27B	262k	Alibaba	37	$0.90	56	3.80	114.89	Model Providers
MiMo-V2-Omni-0327	256k	Xiaomi	36*	$0.34	78	3.00	34.98	Model Providers
Grok 4.3 (medium)	1M	xAI	36*	$0.64	151	8.40	11.72	Model Providers
Claude Sonnet 4.6 (Non-reasoning)	1M	Anthropic	36*	$2.31	43	1.24	12.90	Model Providers
Grok 4.3 (low)	1M	xAI	35*	$0.64	118	4.65	8.88	Model Providers
GLM-5.1	200k	Z AI	35*	$0.90	55	1.95	11.02	Model Providers
MiMo-V2-Omni	256k	Xiaomi	35*	$0.00	79	2.65	34.43	Model Providers
Gemini 3.5 Flash (minimal)	1M	Google	35*	$1.31	167	0.90	3.89	Model Providers
Kimi K2.6	256k	Kimi	35*	$0.70	45	2.78	13.98	Model Providers
GLM 5V Turbo	200k	Z AI	34*	--	--	--	--	Model Providers
Claude Sonnet 4.6 (Non-reasoning, Low Effort)	1M	Anthropic	34*	$2.31	44	1.28	12.72	Model Providers
Qwen3.5 397B A17B	262k	Alibaba	34	$0.90	51	2.74	74.40	Model Providers
Hy3-preview	256k	Tencent	34*	$0.10	115	3.77	25.51	Model Providers
GPT-5.5 Instant (May 2026)	400k	OpenAI	34*	$4.35	--	--	--	Model Providers
MiMo-V2-Flash (Feb 2026)	256k	Xiaomi	33*	$0.06	86	2.52	31.70	Model Providers
GPT-5.5 (Non-reasoning)	922k	OpenAI	33*	$4.35	56	0.99	9.92	Model Providers
Qwen3.5 122B A10B	262k	Alibaba	32	$0.68	135	2.51	20.97	Model Providers
Qwen3.5 397B A17B	262k	Alibaba	32*	$0.90	52	2.65	12.34	Model Providers
Qwen3.6 35B A3B	262k	Alibaba	32	$0.37	171	2.47	36.88	Model Providers
DeepSeek V4 Pro	1M	DeepSeek	31*	$0.18	79	1.78	8.11	Model Providers
Qwen3.5 Omni Plus	256k	Alibaba	31*	$0.84	52	2.44	12.04	Model Providers
Ring-2.6-1T	262k	InclusionAI	31	$0.52	132	3.46	22.35	Model Providers
o3	200k	OpenAI	30*	$1.55	136	6.55	10.23	Model Providers
GPT-5.4 nano	400k	OpenAI	30*	$0.18	170	4.39	7.33	Model Providers
Mistral Medium 3.5	256k	Mistral	30	$1.16	138	2.17	20.31	Model Providers
GPT-5.4 mini (medium)	400k	OpenAI	30*	$0.65	156	4.35	7.55	Model Providers
Step 3.7 Flash	256k	StepFun	30	$0.18	384	0.95	7.46	Model Providers
Claude 4.5 Haiku	200k	Anthropic	30	$0.77	105	12.82	17.60	Model Providers
Gemma 4 31B	256k	Google	29	$0.00	35	1.08	65.65	Model Providers
Command A+	192k	Cohere	29*	$0.00	199	0.39	12.94	Model Providers
Qwen3.6 27B	262k	Alibaba	29*	$0.90	62	3.74	11.86	Model Providers
DeepSeek V4 Flash	1M	DeepSeek	29*	$0.06	107	1.34	6.03	Model Providers
JT-35B-Flash	256k	China Mobile	28*	--	--	--	--	Model Providers
Qwen3.5 122B A10B	262k	Alibaba	28*	$0.68	156	2.47	5.68	Model Providers
MiMo-V2.5-Pro	1M	Xiaomi	28*	$0.58	56	2.79	11.67	Model Providers
Gemini 2.5 Pro	1M	Google	27*	$1.34	124	17.34	21.39	Model Providers
Hy3-preview	256k	Tencent	26*	$0.10	131	4.33	8.14	Model Providers
Ling-2.6-1T	262k	InclusionAI	26*	$0.52	--	--	--	Model Providers
Step 3.5 Flash 2603	256k	StepFun	26*	$0.06	205	1.17	13.36	Model Providers
Doubao Seed Code	256k	ByteDance Seed	26*	--	--	--	--	Model Providers
Gemma 4 26B A4B	256k	Google	26	$0.14	--	--	--	Model Providers
NVIDIA Nemotron 3 Super	1M	NVIDIA	25	$0.28	146	1.18	18.27	Model Providers
Mercury 2	128k	Inception	25*	$0.14	900	3.60	4.15	Model Providers
Gemini 3.1 Flash-Lite	1M	Google	25	$0.22	286	5.39	7.14	Model Providers
Qwen3.5 9B	262k	Alibaba	25*	$0.11	63	1.55	41.31	Model Providers
Gemma 4 31B	256k	Google	25*	$0.17	40	2.25	14.73	Model Providers
Grok 4.3 (Non-reasoning)	1M	xAI	25	$0.64	129	0.71	4.59	Model Providers
K-EXAONE	256k	LG AI Research	25*	--	--	--	--	Model Providers
Trinity Large Thinking	512k	Arcee AI	24*	$0.24	158	1.08	16.92	Model Providers
Qwen3.6 35B A3B	262k	Alibaba	24*	$0.56	183	2.33	5.06	Model Providers
gpt-oss-120b (high)	131k	OpenAI	24	$0.20	340	0.95	8.30	Model Providers
Claude 4.5 Haiku	200k	Anthropic	24*	$0.77	89	0.79	6.39	Model Providers
Qwen3.5 35B A3B	262k	Alibaba	23*	$0.42	172	2.42	5.33	Model Providers
MiMo-V2-Flash	256k	Xiaomi	23*	$0.12	93	4.02	9.41	Model Providers
EXAONE 4.5 33B	262k	LG AI Research	23*	--	--	--	--	Model Providers
HyperNova 60B 2605	131k	Multiverse Computing	22*	$0.05	362	0.69	7.60	Model Providers
Gemma 4 12B	256k	Google	22*	$0.12	124	2.43	22.64	Model Providers
ERNIE 5.0 Thinking Preview	128k	Baidu	22*	--	--	--	--	Model Providers
Nova 2.0 Pro Preview (medium)	256k	Amazon	22	$1.47	126	12.53	32.33	Model Providers
Nemotron Cascade 2 30B A3B	1M	NVIDIA	21*	--	--	--	--	Model Providers
Qwen3 Coder Next	256k	Alibaba	21*	$0.43	63	2.00	9.97	Model Providers
Nova 2.0 Omni (medium)	1M	Amazon	21*	$0.52	--	--	--	Model Providers
Mistral Small 4	256k	Mistral	21*	$0.20	170	0.77	15.43	Model Providers
North Mini Code	256k	Cohere	21*	$0.00	151	0.33	16.88	Model Providers
Nova 2.0 Lite (high)	1M	Amazon	21*	$0.52	144	22.47	39.77	Model Providers
Qwen3.5 9B	262k	Alibaba	20*	--	--	--	--	Model Providers
Magistral Medium 1.2	128k	Mistral	20*	$2.30	41	1.77	62.10	Model Providers
Gemma 4 26B A4B	256k	Google	20*	$0.16	40	1.93	14.32	Model Providers
Qwen3.5 4B	262k	Alibaba	20*	$0.04	31	0.88	80.26	Model Providers
Qwen3 Next 80B A3B	262k	Alibaba	20*	$1.05	174	2.24	16.58	Model Providers
Nova 2.0 Pro Preview (low)	256k	Amazon	20*	$2.13	120	9.73	30.52	Model Providers
Ling 2.6 Flash	262k	InclusionAI	19*	$0.06	--	--	--	Model Providers
Nova 2.0 Lite (medium)	1M	Amazon	19*	$0.52	139	24.73	42.73	Model Providers
Qwen3.5 Omni Flash	256k	Alibaba	19*	$0.17	249	1.97	3.98	Model Providers
JT-MINI	128k	China Mobile	19*	--	--	--	--	Model Providers
Nova 2.0 Lite (low)	1M	Amazon	18*	$0.52	141	15.41	33.15	Model Providers
gpt-oss-120b (low)	131k	OpenAI	18*	$0.20	357	0.89	7.90	Model Providers
GPT-5.4 nano	400k	OpenAI	18*	$0.18	164	0.59	3.63	Model Providers
NVIDIA Nemotron 3 Nano	1M	NVIDIA	18*	$0.07	97	1.75	27.52	Model Providers
LongCat Flash Lite	256k	LongCat	17*	$0.00	--	--	--	Model Providers
K-EXAONE	256k	LG AI Research	17*	--	--	--	--	Model Providers
GPT-5.4 mini	400k	OpenAI	17*	$0.65	147	0.68	4.09	Model Providers
Nova 2.0 Omni (low)	1M	Amazon	17*	$0.52	--	--	--	Model Providers
Nova 2.0 Pro Preview	256k	Amazon	16*	$2.13	122	1.09	5.20	Model Providers
Mi:dm K 2.5 Pro	128k	Korea Telecom	16*	--	--	--	--	Model Providers
Mistral Large 3	256k	Mistral	16*	$0.60	51	1.18	11.04	Model Providers
Qwen3.5 4B	262k	Alibaba	16*	$0.04	33	0.88	15.92	Model Providers
INTELLECT-3	131k	Prime Intellect	16*	--	--	--	--	Model Providers
Devstral 2	256k	Mistral	15*	$0.00	43	1.46	13.12	Model Providers
Solar Open 100B	128k	Upstage	15*	--	--	--	--	Model Providers
Nemotron 3 Nano Omni 30B A3B Reasoning	256k	NVIDIA	15*	$0.10	281	1.02	9.93	Model Providers
gpt-oss-20B (high)	131k	OpenAI	15	$0.07	217	0.79	12.32	Model Providers
gpt-oss-20B (low)	131k	OpenAI	14*	$0.07	224	0.85	12.02	Model Providers
Llama 4 Maverick	1M	Meta	14	$0.34	93	0.99	6.38	Model Providers
Solar Pro 3	128k	Upstage	14	--	--	--	--	Model Providers
Qwen3 Next 80B A3B	262k	Alibaba	14*	$0.65	177	2.23	5.05	Model Providers
Gemma 4 12B (Non-reasoning)	262k	Google	13*	$0.12	133	2.84	6.59	Model Providers
Devstral Small 2	256k	Mistral	13*	$0.00	56	1.22	10.14	Model Providers
Motif-2-12.7B	128k	Motif Technologies	13*	--	--	--	--	Model Providers
Nova Premier	1M	Amazon	13*	$2.18	33	2.93	18.00	Model Providers
Gemma 4 E4B	128k	Google	12*	--	--	--	--	Model Providers
Llama Nemotron Super 49B v1.5	128k	NVIDIA	12*	$0.13	50	1.24	51.60	Model Providers
Mistral Small 4	256k	Mistral	12*	$0.20	156	0.81	4.02	Model Providers
MiniCPM5-1B	128k	OpenBMB	12*	--	--	--	--	Model Providers
Magistral Small 1.2	128k	Mistral	12*	$0.60	108	0.88	24.12	Model Providers
Sarvam 105B (high)	128k	Sarvam	12*	$0.04	97	2.11	27.78	Model Providers
Nova 2.0 Lite	1M	Amazon	12*	$0.52	132	1.30	5.10	Model Providers
MiniCPM5-1B	128k	OpenBMB	12*	--	--	--	--	Model Providers
EXAONE 4.0 32B	131k	LG AI Research	11*	--	--	--	--	Model Providers
Nova 2.0 Omni	1M	Amazon	11*	$0.52	--	--	--	Model Providers
Qwen3.5 2B	262k	Alibaba	10*	$0.03	38	0.76	66.20	Model Providers
Nanbeige4.1-3B	256k	Nanbeige	10*	--	--	--	--	Model Providers
Llama 4 Scout	10M	Meta	10	$0.22	107	0.84	5.50	Model Providers
Ministral 3 14B	256k	Mistral	10*	$0.20	92	0.87	6.29	Model Providers
Falcon-H1R-7B	256k	TII UAE	10*	--	--	--	--	Model Providers
Qwen3 Omni 30B A3B	65.5k	Alibaba	10*	$0.32	85	2.02	31.44	Model Providers
Step3 VL 10B	65.5k	StepFun	9*	--	--	--	--	Model Providers
Gemma 4 E2B	128k	Google	9*	--	--	--	--	Model Providers
Llama Nemotron Ultra	128k	NVIDIA	9*	$0.72	51	2.39	50.95	Model Providers
ERNIE 4.5 300B A47B	131k	Baidu	9*	$0.36	--	--	--	Model Providers
Solar Pro 2	65.5k	Upstage	9*	--	--	--	--	Model Providers
NVIDIA Nemotron Nano 12B v2 VL	128k	NVIDIA	9*	$0.24	283	0.43	9.27	Model Providers
Ministral 3 8B	256k	Mistral	9*	$0.15	102	0.70	5.61	Model Providers
Gemma 4 E4B	128k	Google	9*	--	--	--	--	Model Providers
Granite 4.1 30B	131k	IBM	9	--	--	--	--	Model Providers
NVIDIA Nemotron Nano 9B V2	131k	NVIDIA	9*	$0.05	93	5.14	32.13	Model Providers
NVIDIA Nemotron 3 Nano 4B	262k	NVIDIA	9*	--	--	--	--	Model Providers
Qwen3.5 2B	262k	Alibaba	9*	$0.03	31	0.80	16.87	Model Providers
Llama Nemotron Super 49B v1.5	128k	NVIDIA	9*	$0.13	49	1.25	11.38	Model Providers
Llama 3.3 70B	128k	Meta	9*	$0.59	92	1.61	7.04	Model Providers
Kimi Linear 48B A3B Instruct	1M	Kimi	9*	--	--	--	--	Model Providers
Llama 3.1 405B	128k	Meta	9*	$3.13	66	2.36	9.94	Model Providers
LFM2.5-8B-A1B	32.8k	Liquid AI	8*	$0.00	231	2.78	13.61	Model Providers
Ring-flash-2.0	128k	InclusionAI	8*	$0.18	--	--	--	Model Providers
Solar Pro 2	65.5k	Upstage	8*	--	--	--	--	Model Providers
Command A	256k	Cohere	8*	$3.25	73	1.59	8.40	Model Providers
Llama 3.1 Nemotron 70B	128k	NVIDIA	8*	$1.20	304	5.00	6.64	Model Providers
NVIDIA Nemotron 3 Nano	1M	NVIDIA	7*	$0.07	90	0.40	5.97	Model Providers
NVIDIA Nemotron Nano 9B V2	131k	NVIDIA	7*	$0.06	158	1.56	4.72	Model Providers
Granite 4.1 8B	131k	IBM	7*	$0.06	121	0.83	4.96	Model Providers
Sarvam 30B (high)	65.5k	Sarvam	7*	$0.03	165	1.90	17.07	Model Providers
Gemma 4 E2B	128k	Google	6*	--	--	--	--	Model Providers
R1 1776	128k	Perplexity	6*	--	--	--	--	Model Providers
Llama 3.2 90B (Vision)	128k	Meta	6*	$1.38	58	1.16	9.77	Model Providers
EXAONE 4.0 32B	131k	LG AI Research	6*	--	--	--	--	Model Providers
Ministral 3 3B	256k	Mistral	6*	$0.10	182	0.56	3.30	Model Providers
Jamba 1.7 Large	256k	AI21 Labs	5*	$2.60	59	1.65	10.07	Model Providers
Granite 4.0 H Small	128k	IBM	5*	$0.08	415	10.30	11.51	Model Providers
Qwen3 Omni 30B A3B	65.5k	Alibaba	5*	$0.32	95	1.92	7.18	Model Providers
Qwen3.5 0.8B	262k	Alibaba	5*	$0.01	33	0.80	76.59	Model Providers
LFM2 24B A2B	32.8k	Liquid AI	5*	$0.04	130	0.61	4.44	Model Providers
Phi-4	16k	Microsoft	5*	$0.16	40	1.99	14.53	Model Providers
Nova Micro	130k	Amazon	5*	$0.03	306	0.98	2.62	Model Providers
NVIDIA Nemotron Nano 12B v2 VL	128k	NVIDIA	5*	$0.24	213	0.84	3.18	Model Providers
Phi-4 Multimodal	128k	Microsoft	5*	$0.00	16	1.78	32.81	Model Providers
Qwen3.5 0.8B	262k	Alibaba	4*	$0.01	38	0.87	14.07	Model Providers
MiniCPM-V 4.6 1.3B	262k	OpenBMB	4	--	--	--	--	Model Providers
Jamba Reasoning 3B	262k	AI21 Labs	4*	--	--	--	--	Model Providers
Reka Flash 3	128k	Reka AI	4*	$0.26	--	--	--	Model Providers
Ling-mini-2.0	131k	InclusionAI	4*	--	--	--	--	Model Providers
Llama 3.2 11B (Vision)	128k	Meta	3*	$0.25	52	0.75	10.46	Model Providers
Granite 4.1 3B	131k	IBM	3*	--	--	--	--	Model Providers
Phi-4 Mini	128k	Microsoft	3*	$0.00	45	0.89	11.89	Model Providers
Exaone 4.0 1.2B	64k	LG AI Research	3*	--	--	--	--	Model Providers
Exaone 4.0 1.2B	64k	LG AI Research	3*	--	--	--	--	Model Providers
LFM2.5-1.2B-Thinking	32k	Liquid AI	3*	--	--	--	--	Model Providers
Jamba 1.7 Mini	258k	AI21 Labs	3*	--	--	--	--	Model Providers
LFM2 2.6B	32.8k	Liquid AI	3*	$0.00	337	1.44	2.92	Model Providers
LFM2.5-1.2B-Instruct	32k	Liquid AI	3*	$0.00	497	1.41	2.41	Model Providers
Granite 4.0 H 1B	128k	IBM	3*	--	--	--	--	Model Providers
Gemma 3 270M	32k	Google	2*	--	--	--	--	Model Providers
Apertus 70B Instruct	65.5k	Swiss AI Initiative	2*	$1.03	--	--	--	Model Providers
Granite 4.0 Micro	128k	IBM	2*	--	--	--	--	Model Providers
Granite 4.0 1B	128k	IBM	2*	--	--	--	--	Model Providers
LFM2 8B A1B	32.8k	Liquid AI	2*	$0.00	--	--	--	Model Providers
LFM2.5-VL-1.6B	32k	Liquid AI	1*	$0.00	422	1.50	2.69	Model Providers
Granite 4.0 350M	32.8k	IBM	1*	--	--	--	--	Model Providers
Tiny Aya Global	8.19k	Cohere	1*	$0.00	--	--	--	Model Providers
Apertus 8B Instruct	65.5k	Swiss AI Initiative	1*	$0.11	--	--	--	Model Providers
Granite 4.0 H 350M	32.8k	IBM	1*	--	--	--	--	Model Providers
EXAONE 4.5 33B	262k	LG AI Research	--	--	--	--	--	Model Providers
Gemini 3 Deep Think	128k	Google	--	--	--	--	--	Model Providers
Mi:dm K 2.5 Pro Preview	128k	Korea Telecom	--	--	--	--	--	Model Providers
GPT-5.5 Pro (xhigh)	922k	OpenAI	--	--	--	--	--	Model Providers

Key definitions

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.

Frequently Asked Questions

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) currently ranks #1 on the Artificial Analysis LLM Leaderboard with an Intelligence Index score of 60, out of 47 models ranked.

The top models by Intelligence Index are: 1. Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) (60), 2. Claude Opus 4.8 (Adaptive Reasoning, Max Effort) (56), 3. GPT-5.5 (xhigh) (55), 4. Claude Opus 4.7 (Adaptive Reasoning, Max Effort) (54), 5. GPT-5.5 (high) (53).

Mercury 2 is the fastest at 900.3 tokens per second, followed by LFM2.5-1.2B-Instruct (497.3 t/s) and LFM2 1.2B (438.5 t/s).

Qwen3.5 0.8B (Non-reasoning) is the most affordable at $0.01 per 1M tokens (blended 7:2:1 cache hit/input/output ratio), followed by Qwen3.5 0.8B (Reasoning) ($0.01) and Gemma 3n E4B Instruct ($0.02).

GLM-5.2 (max) is the highest-ranked open weights model with an Intelligence Index score of 51. There are 26 open weights models out of 47 total on the leaderboard.

The top open weights models by Intelligence Index are: 1. GLM-5.2 (max) (51), 2. MiniMax-M3 (44), 3. DeepSeek V4 Pro (Reasoning, Max Effort) (44).

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) leads among 42 reasoning models with an Intelligence Index score of 60. Reasoning models use extended thinking to solve complex problems before responding.

The leaderboard includes filters to narrow results by model type (reasoning vs non-reasoning), openness (open weights vs proprietary), and other criteria. You can also adjust prompt options to see how performance varies with different input lengths.

Click on any model name in the leaderboard to visit its dedicated comparison page with detailed charts covering intelligence, pricing, speed, latency, and more. You can also compare API providers for each model. View all models

LLM Leaderboard - Comparison of over 100 AI models from OpenAI, Google, DeepSeek & others

Intelligence

Output Speed

Latency

Price

Context Window

Key definitions

Context Window

Output Speed

Latency (Time to First Token)

Price

Output Price

Input Price

Time Period

Frequently Asked Questions

Which AI model ranks #1 on the LLM Leaderboard?

What are the top models on the LLM Leaderboard?

Which AI model has the fastest output speed?

Which AI model is the most affordable?

Which is the best open weights model on the leaderboard?

What are the top open weights models on the leaderboard?

Which is the best reasoning model on the leaderboard?

How do I filter models on the leaderboard?

Where can I see more detailed metrics for a model?