LLM Leaderboard

Ranked by LMArena Elo · source LMArena

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

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

#1 by LMArena Elo

Claude Opus 4.6 (Adaptive Reasoning, Max Effort)

1497

Anthropic · in $5.00 / out $25.0 per 1M · 46 tok/s

#	Model	Creator	LMArena	In $/1M	Out $/1M	tok/s	LMArena
1	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	1497	$5.00	$25.0	46	1497
2	Claude Opus 4.6 (Non-reasoning, High Effort)	Anthropic	1497	$5.00	$25.0	43	1497
3	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	1493	$10.0	$50.0	57	1493
4	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)	Anthropic	1482	$5.00	$25.0	50	1482
5	Claude Opus 4.7 (Non-reasoning, High Effort)	Anthropic	1482	$5.00	$25.0	43	1482
6	Muse Spark 1.1 (xhigh)	Meta	1481	$1.25	$4.25	107	1481
7	Gemini 3.5 Flash (high)	Google	1480	$1.50	$9.00	282	1480
8	Gemini 3 Pro Preview (high)	Google	1480	$2.00	$12.0	0	1480
9	Gemini 3 Pro Preview (low)	Google	1480	$2.00	$12.0	0	1480
10	Gemini 3.1 Pro Preview	Google	1479	$2.00	$12.0	127	1479
11	Qwen3.7 Max	Alibaba	1476	$2.50	$7.50	204	1476
12	Gemini 3.5 Flash (medium)	Google	1475	$1.50	$9.00	266	1475
13	Kimi K3	Kimi	1473	$3.00	$15.0	59	1473
14	Muse Spark	Meta	1473	$0.00	$0.00	0	1473
15	GPT-5.5 (high)	OpenAI	1470	$5.00	$30.0	66	1470
16	GLM-5.1 (Reasoning)	Z AI	1466	$1.40	$4.40	70	1466
17	GLM-5.1 (Non-reasoning)	Z AI	1466	$1.40	$4.40	57	1466
18	Gemini 3 Flash Preview (Reasoning)	Google	1466	$0.50	$3.00	224	1466
19	Gemini 3 Flash Preview (Non-reasoning)	Google	1466	$0.50	$3.00	216	1466
20	GPT-5.5 (xhigh)	OpenAI	1464	$5.00	$30.0	80	1464
21	GPT-5.5 (medium)	OpenAI	1464	$5.00	$30.0	69	1464
22	GPT-5.5 (low)	OpenAI	1464	$5.00	$30.0	68	1464
23	GPT-5.5 (Non-reasoning)	OpenAI	1464	$5.00	$30.0	66	1464
24	GPT-5.5 Instant (May 2026)	OpenAI	1464	$5.00	$30.0	0	1464
25	GPT-5.5 Instant (June 2026)	OpenAI	1464	$5.00	$30.0	0	1464
26	GPT-5.5 Pro (xhigh)	OpenAI	1464	$0.00	$0.00	0	1464
27	GLM-5.2 (max)	Z AI	1463	$1.40	$4.40	176	1463
28	MiMo-V2.5-Pro	Xiaomi	1462	$0.43	$0.87	64	1462
29	MiMo-V2.5-Pro (Non-reasoning)	Xiaomi	1462	$0.66	$1.72	64	1462
30	Qwen3.7 Plus	Alibaba	1459	$0.40	$1.60	54	1459
31	Gemini 2.5 Pro	Google	1457	$1.25	$10.0	145	1457
32	Gemini 2.5 Pro Preview (Mar' 25)	Google	1457	$0.00	$0.00	0	1457
33	Gemini 2.5 Pro Preview (May' 25)	Google	1457	$1.25	$10.0	0	1457
34	GPT-5.6 Sol (xhigh)	OpenAI	1457	$5.00	$30.0	63	1457
35	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	1457	$3.00	$15.0	61	1457
36	Claude Sonnet 4.6 (Non-reasoning, High Effort)	Anthropic	1457	$3.00	$15.0	44	1457
37	Claude Sonnet 4.6 (Non-reasoning, Low Effort)	Anthropic	1457	$3.00	$15.0	45	1457
38	Kimi K2.6	Kimi	1455	$0.95	$4.00	47	1455
39	Kimi K2.6 (Non-reasoning)	Kimi	1455	$0.95	$4.00	39	1455
40	Kimi K2	Kimi	1455	$0.57	$2.30	36	1455
41	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)	Anthropic	1454	$5.00	$25.0	52	1454
42	GPT-5.4 (xhigh)	OpenAI	1453	$2.50	$15.0	164	1453
43	GPT-5.4 mini (xhigh)	OpenAI	1453	$0.75	$4.50	177	1453
44	GPT-5.4 (low)	OpenAI	1453	$2.50	$15.0	103	1453
45	GPT-5.4 nano (xhigh)	OpenAI	1453	$0.20	$1.25	166	1453
46	GPT-5.4 nano (medium)	OpenAI	1453	$0.20	$1.25	165	1453
47	GPT-5.4 mini (medium)	OpenAI	1453	$0.75	$4.50	165	1453
48	GPT-5.4 (Non-reasoning)	OpenAI	1453	$2.50	$15.0	100	1453
49	GPT-5.4 nano (Non-Reasoning)	OpenAI	1453	$0.20	$1.25	172	1453
50	GPT-5.4 mini (Non-Reasoning)	OpenAI	1453	$0.75	$4.50	164	1453

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.