Comprehensive AI Model Rankings: Performance Comparison of Over 30 LLMs

Explore our detailed ranking of over 30 AI models, including GPT-4o, Llama 3, and more. Compare key metrics such as quality, speed, latency, and pricing to find the best AI model for your needs. Stay informed with the latest insights on leading large language models (LLMs) and their performance.

model	creator	context	quality	price (USD / 1M tokens)	speed (tokens/second)	latency (first chunk/s)
o1-preview	OpenAI	128k	85	26.25	31.4	33.09
o1-mini	OpenAI	128k	82	5.25	72.5	14.51
GPT-4o (Aug '24)	OpenAI	128k	77	4.38	104.1	0.39
GPT-4o (May '24)	OpenAI	128k	77	7.5	110.9	0.37
Claude 3.5 Sonnet	Anthropic	200k	77	6	68.3	0.94
Qwen2.5 72B	Alibaba	131k	75	0.38	29.6	0.58
GPT-4 Turbo	OpenAI	128k	74	15	38.4	0.57
Mistral Large 2	Mistral	128k	73	3.75	37.5	0.52
Gemini 1.5 Pro	Google	2m	72	5.25	64.9	0.8
Llama 3.1 405B	Meta	128k	72	5	27.8	0.65
GPT-4o mini	OpenAI	128k	71	0.26	130.4	0.39
Claude 3 Opus	Anthropic	200k	70	30	24.9	1.75
Qwen2 72B	Alibaba	128k	69	0.63	51.3	0.34
DeepSeek-Coder-V2	DeepSeek	128k	67	0.17	16.8	1.14
DeepSeek-V2	DeepSeek	128k	66	0.17	16.8	1.22
DeepSeek-V2.5	DeepSeek	128k	66	0.17	16.8	1.21
Llama 3.1 70B	Meta	128k	65	0.88	77.1	0.38
Jamba 1.5 Large	AI21 Labs	256k	64	3.5	61.5	1.02
Sonar Large	Perplexity	33k	62	1	45.7	0.24
Llama 3 70B	Meta	8k	62	0.9	54.4	0.44
Mixtral 8x22B	Mistral	65k	61	1.2	59.2	0.34
Mistral Small (Sep '24)	Mistral	128k	60	0.3	80.2	0.44
Gemini 1.5 Flash	Google	1m	60	0.13	310.5	0.37
Yi-Large	01.AI	32k	58	3	63.9	0.39
Claude 3 Sonnet	Anthropic	200k	57	6	53.7	0.96
Reka Core	Reka AI	128k	57	4	14.5	1.13
Command-R+ (Aug '24)	Cohere	128k	56	5.19	47.8	0.53
Mistral Large	Mistral	33k	56	6	35	0.47
Claude 3 Haiku	Anthropic	200k	54	0.5	131.1	0.48
GPT-3.5 Turbo	OpenAI	16k	53	0.75	83.7	0.38
Llama 3.1 8B	Meta	128k	53	0.14	278.4	0.3
Mistral NeMo	Mistral	128k	52	0.15	134.1	0.25
Command-R (Aug '24)	Cohere	128k	51	0.51	106.6	0.35
Mistral Small (Feb '24)	Mistral	33k	50	1.5	47.9	0.42
DBRX	Databricks	33k	50	1.16	86.5	0.44
Gemma 2 27B	Google	8k	49	0.8	66.4	0.36
Gemma 2 9B	Google	8k	47	0.2	114.2	0.27
Llama 3 8B	Meta	8k	46	0.15	98.3	0.35
Jamba 1.5 Mini	AI21 Labs	256k	46	0.25	162.5	0.8
Command-R+ (Apr '24)	Cohere	128k	46	6	47.2	0.56
Reka Flash	Reka AI	128k	46	1.1	29.9	0.97
OpenChat 3.5	OpenChat	8k	43	0.06	69.5	0.28
Mixtral 8x7B	Mistral	33k	42	0.5	86.6	0.33
Sonar Small	Perplexity	33k	41	0.2	141.8	0.19
Command-R (Mar '24)	Cohere	128k	36	0.75	106.2	0.39
Codestral-Mamba	Mistral	256k	36	0.25	94.9	0.55
Llama 2 Chat 70B	Meta	4k	34	1.39	47.6	0.36
Reka Edge	Reka AI	64k	30	0.55	0	0
Gemma 7B	Google	8k	28	0.07	1	0.85
Jamba Instruct	AI21 Labs	256k	28	0.55	77.9	0.73
Command	Cohere	4k	26	1.44	21.9	0.52
Llama 2 Chat 13B	Meta	4k	25	0.3	53.6	0.4
Mistral 7B	Mistral	33k	24	0.16	107.3	0.28
Command Light	Cohere	4k	14	0.38	34.4	0.54
Llama 2 Chat 7B	Meta	4k	10	0.33	122.6	0.25
Phi-3 Medium 14B	Microsoft Azure	128k	0	0.45	55	0.41
Codestral	Mistral	33k	0	0.3	49.6	0.48
Mistral Medium	Mistral	33k	0	4.09	38.3	0.81
Sonar 3.1 Large	Perplexity	131k	0	1	58.9	0.21
GPT-4	OpenAI	8k	0	37.5	28.3	0.58
Claude 2.0	Anthropic	100k	0	12	31.3	1.08
Claude Instant	Anthropic	100k	0	1.2	74.9	0.57
Claude 2.1	Anthropic	200k	0	12	28.4	1.58
GPT-3.5 Turbo Instruct	OpenAI	4k	0	1.63	107.8	0.53
Gemini 1.0 Pro	Google	33k	0	0.75	99.7	1.18
Sonar 3.1 Small	Perplexity	131k	0	0.2	135.6	0.18
Pixtral 12B	Mistral	128k	0	0.15	80	0.59