🏟️ Arena AI 排行榜

LMSYS 团队运营的真实人类盲投 ELO 榜 · 6 大维度 · 27,551,386.73 投票 · 自动 1 小时刷新

实时抓取缓存 1h

💬 Text Leaderboard · Top 30

通用文本对话 ELO 榜（盲投最多） · 409 模型（榜单共 409 名）·12,309,852 票

Rank	Model	Provider	Score (95% CI)	Votes	$ / M	Context
1	claude-opus-5.5-high Anthropic	Anthropic	1509 ±12	2,307	$4 / $20	1M
2	claude-opus-4-6-high Anthropic	Anthropic	1505 ±3	76,518	$5 / $25	1M
3	claude-fable-5-high Anthropic	Anthropic	1504 ±4	36,462	$10 / $50	1M
4	claude-opus-4-7-high Anthropic	Anthropic	1502 ±4	64,007	$5 / $25	1M
5	claude-fable-5.1-max Anthropic	Anthropic	1501 ±7	9,942	$10 / $50	1M
6	claude-opus-4-6 Anthropic	Anthropic	1498 ±3	80,836	$5 / $25	1M
7	muse-spark-1.2 (xHigh) Meta	Meta	1496 ±10	3,422	$1.25 / $4.25	N/A
8	claude-opus-4-7 Anthropic	Anthropic	1495 ±4	65,051	$5 / $25	1M
9	muse-spark-1.3-max Meta	Meta	1494 ±7	10,036	$1.25 / $4.25	1M
10	Google	gemini-3.8-flash-high	1492 ±5	21,728	$0.75 / $3.75	1M
11	claude-opus-5-high Anthropic	Anthropic	1491 ±4	55,063	$5 / $25	1M
12	muse-spark-1.1 Meta	Meta	1491 ±5	34,760	$1.25 / $4.25	N/A
13	muse-spark Meta	Meta	1489 ±6	14,131	N/A	N/A
14	claude-opus-5-max Anthropic	Anthropic	1488 ±5	26,760	$5 / $25	1M
15	Google	gemini-3.7-flash-high	1488 ±5	19,044	$0.75 / $3.75	1M
16	Moonshot	kimi-k3-max	1488 ±5	26,400	N/A	N/A
17	Google	gemini-3.1-pro-preview	1487 ±3	119,196	$1 / $6	1M
18	Google	gemini-3-pro	1485 ±4	41,921	$2 / $12	1M
19	OpenAI	gpt-5.6-sol-xhigh	1483 ±5	34,258	$4 / $20	N/A
20	Google	gemini-3.6-flash-high	1482 ±5	33,739	$0.75 / $3.75	1M
21	OpenAI	gpt-5.5-high	1481 ±4	69,008	$5 / $30	1.1M
22	claude-opus-4-8-high Anthropic	Anthropic	1480 ±4	61,560	$5 / $25	1M
23	Xiaomi	mimo-v2.6-pro	1480 ±9	4,026	$0.43 / $0.87	1.1M
24	Z.ai	glm-5.3-max	1480 ±6	15,904	$1.40 / $4.40	1M
25	Alibaba	qwen3.8-max	1479 ±5	21,561	$1.69 / $5.07	1M
26	OpenAI	gpt-6-astra-max	1478 ±8	7,185	N/A	N/A
27	Google	gemini-3.5-flash-high	1477 ±4	46,190	$0.75 / $4.50	1M
28	OpenAI	gpt-5.5	1477 ±4	70,635	$5 / $30	1.1M
29	DeepSeek	deepseek-v4.1-flash-max	1477 ±8	6,630	$0.30 / $1.20	1M
30	OpenAI	gpt-5.2-chat-latest-20260210	1476 ±4	35,962	$1.75 / $14	128K

关于数据：Arena.ai 排行榜基于人类对模型两两盲投结果，由 LMSYS Chatbot Arena 团队运营，是 LLM 评测领域公信力最高的 ELO 排名之一。所有分数均含 95% 置信区间，投票数越大分数越稳定。本页 实时抓取 arena.ai/leaderboard/ 5 个端点（text / vision / agent / search / text-to-image，webdev 已下线），缓存 1 小时。