LLM Leaderboard

Ranked by Coding Index · source AA

AA composite — LiveCodeBench, SciCode, etc.

IntelligenceAA LMArenaLMArena CodingAA MathAA MMLU-ProAA GPQAAA LiveCodeAA MATH-500AA AIMEAA HLEAA SciCodeAA

#1 by Coding Index

GPT-5.6 Sol (xhigh)

78.3

OpenAI · in $5.00 / out $30.0 per 1M · 63 tok/s

#	Model	Creator	Coding	In $/1M	Out $/1M	tok/s	LMArena
1	GPT-5.6 Sol (xhigh)	OpenAI	78.3	$5.00	$30.0	63	1457
2	GPT-5.6 Sol (max)	OpenAI	77.4	$5.00	$30.0	65	—
3	GPT-5.6 Sol (high)	OpenAI	77.2	$5.00	$30.0	56	—
4	GPT-5.6 Terra (max)	OpenAI	76.7	$2.50	$15.0	137	—
5	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	76.5	$10.0	$50.0	57	1493
6	GPT-5.6 Sol (medium)	OpenAI	76.3	$5.00	$30.0	55	—
7	Kimi K3	Kimi	76.2	$3.00	$15.0	59	1473
8	GPT-5.5 (xhigh)	OpenAI	74.9	$5.00	$30.0	80	1464
9	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)	Anthropic	74.3	$5.00	$25.0	52	1454
10	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)	Anthropic	73.6	$5.00	$25.0	50	1482
11	Grok 4.5 (high)	SpaceXAI	72.4	$2.00	$6.00	74	1452
12	GPT-5.5 (high)	OpenAI	71.6	$5.00	$30.0	66	1470
13	Claude Sonnet 5 (Adaptive Reasoning, Max Effort)	Anthropic	71.5	$2.00	$10.0	78	—
14	GPT-5.5 (medium)	OpenAI	71.5	$5.00	$30.0	69	1464
15	GPT-5.6 Luna (max)	OpenAI	71.4	$1.00	$6.00	195	—
16	Muse Spark 1.1 (xhigh)	Meta	71.3	$1.25	$4.25	107	1481
17	GPT-5.4 (xhigh)	OpenAI	71.1	$2.50	$15.0	164	1453
18	GPT-5.6 Terra (xhigh)	OpenAI	70.6	$2.50	$15.0	128	—
19	Gemini 3.5 Flash (high)	Google	70.1	$1.50	$9.00	282	1480
20	GPT-5.6 Sol (low)	OpenAI	69.7	$5.00	$30.0	57	—
21	GLM-5.2 (max)	Z AI	68.8	$1.40	$4.40	176	1463
22	Gemini 3.1 Pro Preview	Google	68.8	$2.00	$12.0	127	1479
23	GPT-5.6 Luna (xhigh)	OpenAI	68.6	$1.00	$6.00	205	—
24	GPT-5.6 Terra (high)	OpenAI	67.1	$2.50	$15.0	124	—
25	Claude Sonnet 5 (Non-reasoning, High Effort)	Anthropic	66.4	$2.00	$10.0	59	—
26	Qwen3.7 Max	Alibaba	66.0	$2.50	$7.50	204	1476
27	GPT-5.6 Sol (Non-reasoning)	OpenAI	65.1	$5.00	$30.0	52	—
28	GPT-5.6 Terra (medium)	OpenAI	64.7	$2.50	$15.0	120	—
29	GPT-5.6 Luna (high)	OpenAI	63.3	$1.00	$6.00	199	—
30	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	63.0	$3.00	$15.0	61	1457
31	Kimi K2.6	Kimi	61.8	$0.95	$4.00	47	1455
32	GPT-5.5 (low)	OpenAI	60.9	$5.00	$30.0	68	1464
33	Kimi K2.7 Code	Kimi	60.8	$0.95	$4.00	45	—
34	MiMo-V2.5-Pro	Xiaomi	60.2	$0.43	$0.87	64	1462
35	KAT Coder Pro V2	KwaiKAT	59.5	$0.30	$1.20	0	—
36	DeepSeek V4 Pro (Reasoning, Max Effort)	DeepSeek	59.4	$0.43	$0.87	62	1450
37	Nex-N2-Pro	Nex AGI	59.1	$0.50	$2.50	144	—
38	Hy3	Tencent	58.8	$0.00	$0.00	52	—
39	MiniMax-M3	MiniMax	58.6	$0.30	$1.20	100	1437
40	Muse Spark	Meta	58.6	$0.00	$0.00	0	1473
41	GPT-5.6 Terra (low)	OpenAI	58.1	$2.50	$15.0	120	—
42	MiMo-V2.5	Xiaomi	56.8	$0.14	$0.28	66	1426
43	GPT-5.5 (Non-reasoning)	OpenAI	56.5	$5.00	$30.0	66	1464
44	DeepSeek V4 Flash (Reasoning, Max Effort)	DeepSeek	56.2	$0.14	$0.28	109	1433
45	GPT-5.4 mini (xhigh)	OpenAI	56.1	$0.75	$4.50	177	1453
46	GPT-5.4 nano (xhigh)	OpenAI	56.1	$0.20	$1.25	166	1453
47	Qwen3.7 Plus	Alibaba	55.9	$0.40	$1.60	54	1459
48	GLM-5.1 (Reasoning)	Z AI	55.8	$1.40	$4.40	70	1466
49	Qwen3.6 Plus	Alibaba	54.5	$0.50	$3.00	53	1436
50	Qwen3.6 27B (Reasoning)	Alibaba	53.7	$0.60	$3.60	56	—

Quality, pricing, and speed benchmarks via Artificial Analysis. Human preference Elo via LMArena. Refreshed daily at 06:00 UTC · last sync Sun, 19 Jul 2026 06:00:01 GMT.

About the metrics

Intelligence Index

Artificial Analysis composite of reasoning, knowledge, coding, math.

LMArena Elo

LMArena

Human preference Elo from chatbot arena head-to-head votes.

Coding Index

AA composite — LiveCodeBench, SciCode, etc.

Math Index

AA composite — MATH-500, AIME, etc.

MMLU-Pro

Multi-domain knowledge & reasoning. Harder than MMLU.

GPQA Diamond

Graduate-level science Q&A. Strong reasoning signal.

LiveCodeBench

Competitive programming, contamination-resistant.

MATH-500

Subset of the MATH benchmark.

AIME

American Invitational Mathematics Examination — olympiad math.

Humanity's Last Exam

Frontier reasoning benchmark; most models still score low.

SciCode

Scientific coding tasks.