Reference table

AI model ranking

Compare leading AI models by benchmark score, provider, API price, and output speed.

Methodology

Top score

Claude Opus 5 (Adaptive Reasoning, Max Effort)

63.1

Lowest listed price

G9v3-39A5B

$0.000 / 1M tokens

Fastest

Ling 3.0 Flash

401.7 tok/s

Benchmark board

Model ranking

Rank, model, provider, Artificial Analysis Intelligence Index, blended API price, and output speed.

Rank	Model	Provider	Index	Blended price	Speed
#1	Claude Opus 5 (Adaptive Reasoning, Max Effort)	Anthropic	63.1	$3.850/M	57.6 tok/s
#2	Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	62.5	$3.850/M	60.6 tok/s
#3	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	62.1	$7.700/M	69.7 tok/s
#4	Claude Opus 5 (Adaptive Reasoning, High Effort)	Anthropic	61.5	$3.850/M	61.0 tok/s
#5	GPT-5.6 Sol (max)	OpenAI	60.9	$4.350/M	69.2 tok/s
#6	Kimi K3 (max)	Kimi	59.7	$2.310/M	43.0 tok/s
#7	GPT-5.6 Sol (xhigh)	OpenAI	59.0	$4.350/M	70.7 tok/s
#8	Claude Opus 5 (Adaptive Reasoning, Medium Effort)	Anthropic	58.6	$3.850/M	59.3 tok/s
#9	Qwen3.8 Max	Qwen	58.1	$1.175/M	85.0 tok/s
#10	GPT-5.6 Sol (high)	OpenAI	57.3	$4.350/M	67.7 tok/s
#11	Muse Spark 1.2 (xhigh)	Meta	56.8	$0.780/M	Not listed
#12	GPT-5.6 Terra (max)	OpenAI	56.6	$1.740/M	141.6 tok/s
#13	Grok 4.5 (high)	SpaceXAI	55.8	$1.210/M	60.4 tok/s
#14	GPT-5.6 Sol (medium)	OpenAI	55.6	$4.350/M	69.8 tok/s
#15	Claude Sonnet 5 (Adaptive Reasoning, Max Effort)	Anthropic	55.3	$1.540/M	72.0 tok/s
#16	GPT-5.6 Terra (xhigh)	OpenAI	52.8	$1.740/M	129.0 tok/s
#17	GLM-5.2 (max)	Z.ai	52.6	$0.860/M	122.6 tok/s
#18	Claude Opus 5 (Adaptive Reasoning, Low Effort)	Anthropic	52.5	$3.850/M	58.3 tok/s
#19	GPT-5.6 Luna (max)	OpenAI	52.3	$0.174/M	195.6 tok/s
#20	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)	DeepSeek	51.8	$0.058/M	127.8 tok/s
#21	Gemini 3.6 Flash (high)	Google	51.6	$1.155/M	231.6 tok/s
#22	GPT-5.6 Sol (low)	OpenAI	50.7	$4.350/M	67.7 tok/s
#23	GPT-5.6 Terra (high)	OpenAI	50.1	$1.740/M	139.0 tok/s
#24	GPT-5.6 Luna (xhigh)	OpenAI	50.1	$0.174/M	187.8 tok/s
#25	Kimi K3 (low)	Kimi	48.3	$2.310/M	43.1 tok/s
#26	Gemini 3.1 Pro Preview	Google	47.7	$1.740/M	138.4 tok/s
#27	GPT-5.6 Luna (high)	OpenAI	47.0	$0.174/M	195.7 tok/s
#28	GPT-5.6 Terra (medium)	OpenAI	46.8	$1.740/M	128.3 tok/s
#29	Gemini 3.5 Flash (medium)	Google	46.7	$1.305/M	194.3 tok/s
#30	GPT-5.3 Codex (xhigh)	OpenAI	45.5	$1.873/M	140.9 tok/s
#31	MiniMax-M3	MiniMax	45.4	$0.222/M	112.1 tok/s
#32	DeepSeek V4 Pro (Reasoning, Max Effort)	DeepSeek	45.3	$0.177/M	75.6 tok/s
#33	Motif 3 (Beta)	Motif	44.9	Not listed	Not listed
#34	DeepSeek V4 Pro (Reasoning, High Effort)	DeepSeek	43.7	$0.177/M	75.6 tok/s
#35	Kimi K2.7 Code	Kimi	43.0	$0.723/M	43.2 tok/s
#36	MiMo-V2.5-Pro	Xiaomi	42.9	$0.177/M	79.6 tok/s
#37	Claude Sonnet 5 (Non-reasoning, High Effort)	Anthropic	42.6	$1.540/M	72.1 tok/s
#38	Inkling (xhigh)	Thinking Machines	42.3	$0.724/M	74.4 tok/s
#39	Hy3	Tencent	42.2	$0.107/M	67.9 tok/s
#40	GPT-5.6 Sol (Non-reasoning)	OpenAI	41.9	$4.350/M	61.5 tok/s
#41	Nex-N2-Pro	Nex AGI	41.7	$0.525/M	130.6 tok/s
#42	GPT-5.6 Terra (low)	OpenAI	41.3	$1.740/M	122.4 tok/s
#43	Inkling Small	Thinking Machines	41.2	$0.222/M	144.0 tok/s
#44	JT-4.1 Flash 236B A21B	China Mobile	39.8	Not listed	Not listed
#45	Agnes 2.5 Pro Alpha	Sapiens AI	39.7	$0.183/M	129.9 tok/s
#46	Qwen3.7 Plus	Qwen	39.4	$0.268/M	56.5 tok/s
#47	GPT-5.6 Luna (medium)	OpenAI	38.9	$0.174/M	190.0 tok/s
#48	Nemotron 3 Ultra 550B A55B (Reasoning)	NVIDIA	38.3	$0.535/M	165.2 tok/s
#49	MiMo-V2.5	Xiaomi	38.0	$0.058/M	89.8 tok/s
#50	Ling 3.0 Flash	InclusionAI	37.8	$0.048/M	401.7 tok/s
#51	Qwen3.6 27B (Reasoning)	Qwen	37.7	$0.900/M	58.5 tok/s
#52	Gemini 3.5 Flash-Lite	Google	37.4	$0.331/M	397.4 tok/s
#53	MiMo-V2-Omni-0327	Xiaomi	37.3	Not listed	Not listed
#54	Grok 4.3 (medium)	SpaceXAI	36.9	$0.640/M	133.8 tok/s
#55	Grok 4.3 (low)	SpaceXAI	36.3	$0.640/M	131.1 tok/s
#56	MiMo-V2-Omni	Xiaomi	35.9	Not listed	Not listed
#57	Gemini 3.5 Flash (minimal)	Google	35.8	$1.305/M	167.2 tok/s
#58	Claude Sonnet 4.6 (Non-reasoning, Low Effort)	Anthropic	35.1	$2.310/M	43.8 tok/s
#59	GLM-5.2 (Non-reasoning)	Z.ai	34.8	$1.276/M	114.3 tok/s
#60	GPT-5.6 Terra (Non-reasoning)	OpenAI	34.6	$1.740/M	122.9 tok/s
#61	Qwen3.5 397B A17B (Reasoning)	Qwen	34.3	$0.900/M	74.7 tok/s
#62	MiMo-V2-Flash (Feb 2026)	Xiaomi	34.0	Not listed	Not listed
#63	LongCat 2.0	LongCat	33.9	$0.455/M	43.2 tok/s
#64	KAT Coder Pro V2	KwaiKAT	33.9	$0.222/M	105.8 tok/s
#65	GPT-5.6 Luna (low)	OpenAI	33.9	$0.174/M	170.0 tok/s
#66	Qwen3.5 122B A10B (Reasoning)	Qwen	32.8	$0.680/M	137.7 tok/s
#67	Qwen3.5 397B A17B (Non-reasoning)	Qwen	32.7	$0.900/M	74.0 tok/s
#68	Qwen3.6 35B A3B (Reasoning)	Qwen	32.1	$0.372/M	138.7 tok/s
#69	DeepSeek V4 Pro (Non-reasoning)	DeepSeek	31.9	$0.177/M	73.2 tok/s
#70	G9v3-39A5B	AI9Stars	31.4	$0.000/M	Not listed
#71	Qwen3.5 Omni Plus	Qwen	31.3	$0.840/M	53.4 tok/s
#72	Qwen3.6 27B (Non-reasoning)	Qwen	31.3	$0.900/M	60.9 tok/s
#73	Ring-2.6-1T	InclusionAI	31.1	$0.520/M	131.0 tok/s
#74	o3	OpenAI	31.1	$1.550/M	150.6 tok/s
#75	Step 3.7 Flash	StepFun	30.9	$0.183/M	392.1 tok/s
#76	Mistral Medium 3.5	Mistral	30.4	$1.155/M	141.0 tok/s
#77	Claude 4.5 Haiku (Reasoning)	Anthropic	29.9	$0.770/M	91.8 tok/s
#78	Gemma 4 31B (Reasoning)	Google	29.7	$0.000/M	34.7 tok/s
#79	DeepSeek V4 Flash (Non-reasoning)	DeepSeek	29.3	$0.105/M	Not listed
#80	GPT-5.5 Instant (June 2026)	OpenAI	29.2	$4.350/M	164.3 tok/s

Sources

Updated 2026-08-09. Benchmark methodology and ranking source below. Read how we use the data in themodel ranking methodology.

Artificial Analysis ranking data Artificial Analysis methodology