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 5 (Adaptive Reasoning, High Effort)

1505

Anthropic · in $5.00 / out $25.0 per 1M · 55 tok/s

#	Model	Creator	LMArena	In $/1M	Out $/1M	tok/s	LMArena
1	Claude Opus 5 (Adaptive Reasoning, High Effort)	Anthropic	1505	$5.00	$25.0	55	1505
2	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	1498	$5.00	$25.0	0	1498
3	Claude Opus 4.6 (Non-reasoning, High Effort)	Anthropic	1498	$5.00	$25.0	0	1498
4	Gemini 3.8 Flash (high)	Google	1495	$0.75	$3.75	312	1495
5	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 5 Fallback)	Anthropic	1493	$10.0	$50.0	0	1493
6	Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	1493	$10.0	$50.0	70	1493
7	Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	1493	$10.0	$50.0	65	1493
8	Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	1493	$10.0	$50.0	59	1493
9	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	1493	$10.0	$50.0	69	1493
10	Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	1493	$10.0	$50.0	56	1493
11	Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)	Anthropic	1493	$10.0	$50.0	55	1493
12	Gemini 3.7 Flash (high)	Google	1490	$0.75	$3.75	325	1490
13	Muse Spark 1.3 (max)	Meta	1490	$1.25	$4.25	261	1490
14	Muse Spark 1.2 (xhigh)	Meta	1489	$1.25	$4.25	270	1489
15	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)	Anthropic	1483	$5.00	$25.0	0	1483
16	Claude Opus 4.7 (Non-reasoning, High Effort)	Anthropic	1483	$5.00	$25.0	0	1483
17	Gemini 3.5 Flash (high)	Google	1482	$1.50	$9.00	0	1482
18	Qwen3.8 Max (0902)	Alibaba	1481	$2.00	$6.00	41	1481
19	Qwen3.8 Max	Alibaba	1481	$2.00	$6.00	41	1481
20	Muse Spark 1.1 (xhigh)	Meta	1480	$1.25	$4.25	0	1480
21	Gemini 3.1 Pro Preview	Google	1480	$2.00	$12.0	133	1480
22	Gemini 3 Pro Preview (high)	Google	1479	$2.00	$12.0	0	1479
23	Gemini 3 Pro Preview (low)	Google	1479	$2.00	$12.0	0	1479
24	Gemini 3.6 Flash (high)	Google	1476	$0.75	$3.75	186	1476
25	Gemini 3.5 Flash (medium)	Google	1476	$1.50	$9.00	251	1476
26	GLM-5.3 (max)	Z AI	1475	$1.40	$4.40	59	1475
27	Qwen3.7 Max	Alibaba	1474	$2.50	$7.50	0	1474
28	Muse Spark 1.3 (max)	Meta	1473	$1.25	$4.25	221	1473
29	Muse Spark 1.3 (xhigh)	Meta	1473	$1.25	$4.25	324	1473
30	Muse Spark	Meta	1473	$0.00	$0.00	0	1473
31	Kimi K3 (max)	Kimi	1472	$3.00	$15.0	38	1472
32	GLM 5.3 Flash	Z AI	1472	$0.15	$0.50	111	1472
33	GPT-5.5 (high)	OpenAI	1471	$5.00	$30.0	0	1471
34	GLM-5.2 (max)	Z AI	1467	$1.40	$4.40	73	1467
35	Gemini 3 Flash Preview (Reasoning)	Google	1467	$0.50	$3.00	0	1467
36	Gemini 3 Flash Preview (Non-reasoning)	Google	1467	$0.50	$3.00	0	1467
37	GPT-5.5 (xhigh)	OpenAI	1466	$5.00	$30.0	0	1466
38	GPT-5.5 (medium)	OpenAI	1466	$5.00	$30.0	0	1466
39	GPT-5.5 (low)	OpenAI	1466	$5.00	$30.0	0	1466
40	GPT-5.5 Instant (June 2026)	OpenAI	1466	$5.00	$30.0	145	1466
41	GPT-5.5 (Non-reasoning)	OpenAI	1466	$5.00	$30.0	0	1466
42	GPT-5.5 Instant (May 2026)	OpenAI	1466	$5.00	$30.0	0	1466
43	GPT-5.5 Pro (xhigh)	OpenAI	1466	$0.00	$0.00	0	1466
44	MiMo-V2.5-Pro	Xiaomi	1465	$0.43	$0.87	51	1465
45	MiMo-V2.5-Pro (Non-reasoning)	Xiaomi	1465	$0.43	$0.87	48	1465
46	GLM-5.1 (Reasoning)	Z AI	1462	$1.20	$4.40	0	1462
47	GLM-5.1 (Non-reasoning)	Z AI	1462	$1.38	$4.40	0	1462
48	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	1458	$3.00	$15.0	0	1458
49	Claude Sonnet 4.6 (Non-reasoning, High Effort)	Anthropic	1458	$3.00	$15.0	0	1458
50	Claude Sonnet 4.6 (Non-reasoning, Low Effort)	Anthropic	1458	$3.00	$15.0	59	1458

Quality, pricing, and speed benchmarks via Artificial Analysis. Human preference Elo via LMArena. Refreshed daily at 06:00 UTC · last sync Thu, 17 Sep 2026 06:00:05 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.