Name: Anthropic 参考图网页设计模型排行榜（2026-07-25） | AITNT
Creator: LM Arena
License: https://creativecommons.org/licenses/by/4.0/
Keywords: Anthropic,参考图设计,AI 大语言模型排行榜,AI 模型排行

LM Arena 大模型全球实力榜LM Arena Global AI Leaderboard参考图设计🖼️Reference Design

查看各种 AI 大语言模型在数学推理、代码生成、创意写作及其他开放式文本任务中的综合 Elo 积分排名，数据来源于真实用户的匿名盲测投票。

2026-07-25

▾

上榜模型Models

参赛厂商Providers

47.7K

总投票数Total Votes

📖 指标说明 — 读懂这张榜单📖 Metrics Guide — Understanding the Leaderboard

🎯

榜单主指标（Score）Primary Metric (Score)

每个榜单会采用官网对应的核心排序指标。通用 Arena 榜单通常是模型竞技积分；智能体榜单则展示净提升及多项任务指标。

Each leaderboard uses the official primary ranking metric. Most Arena boards use competitive scores; the Agent board uses net improvement and task-specific metrics.

🔢

精确值（Float Value）Float Value

主指标的完整浮点数值。对于通用 Arena 榜单可用于区分整数分相近的模型；智能体榜单以百分比和置信区间展示。

The full floating-point value of the primary metric. It helps distinguish close scores on standard boards; Agent metrics are shown as percentages with confidence intervals.

📊

方差（Variance）Variance

衡量结果的统计稳定程度。绿色·稳定（<5）更可信；橙色·波动（5~12）；红色·不稳（>12）说明排名还可能明显变化。

Measures statistical stability. Green·Stable (<5); Orange·Unstable (5–12); Red·Volatile (>12) means the ranking may still move significantly.

↔️

置信区间（95% CI = ±N）95% Confidence Interval (CI = ±N)

95% 置信区间反映当前估计的不确定范围，显示为 ±N。在相同计算口径下，N 越小说明估计越集中、排名越稳定。

The 95% confidence interval, shown as ±N, summarizes uncertainty in the current estimate. Under the same methodology, a smaller N indicates a more precise estimate and a more stable ranking.

🗳️

投票数（Vote Count）Vote Count

该模型或厂商参与评测的总次数。数量越高，结果的统计置信度越高、越不容易受单次样本影响而波动。

Total evaluation volume for the model or lab. Higher counts mean higher statistical confidence and less sensitivity to individual samples.

📜

开源协议（License）License

Apache/Llama：完全开源可商用；MIT：开源限制极少；Proprietary：闭源商业模型。协议决定你能否把它集成到自己的产品里。

Apache/Llama: Fully open-source, commercial use allowed; MIT: Open-source, minimal restrictions; Proprietary: Closed-source commercial model. License determines if you can integrate it into your product.

排名Rank	名次区间Rank Range	模型Model		投票数Votes	精确分 & 区间Float Score & CI	方差Variance	价格 ($/1M)Price ($/1M)	上下文Context
🥇	2 - 3	claude-fable-5 Anthropic · Proprietary	1661±20.0	1.4K 票votes	1661.000 [1641.0, 1681.0]	1.00 · 稳定Stable	—	—
🥈	4 - 12	claude-opus-4-7-thinking Anthropic · Proprietary	1584±12.0	3.2K 票votes	1584.000 [1572.0, 1596.0]	8.00 · 波动Unstable	$5 / $25	1M
🥉	4 - 13	claude-opus-4-7 Anthropic · Proprietary	1580±12.0	3.1K 票votes	1580.000 [1568.0, 1592.0]	9.00 · 波动Unstable	$5 / $25	1M
4	4 - 14	claude-opus-4-8-thinking Anthropic · Proprietary	1578±15.0	1.9K 票votes	1578.000 [1563.0, 1593.0]	10.00 · 波动Unstable	—	—
5	4 - 16	claude-opus-4-6-thinking Anthropic · Proprietary	1567±11.0	3.6K 票votes	1567.000 [1556.0, 1578.0]	12.00 · 不稳Volatile	$5 / $25	1M
6	5 - 20	claude-opus-4-8 Anthropic · Proprietary	1554±15.0	1.9K 票votes	1554.000 [1539.0, 1569.0]	15.00 · 不稳Volatile	—	—
7	7 - 19	claude-opus-4-6 Anthropic · Proprietary	1554±11.0	4.0K 票votes	1554.000 [1543.0, 1565.0]	12.00 · 不稳Volatile	$5 / $25	1M
8	4 - 21	claude-sonnet-5-high Anthropic · Proprietary	1552±25.0	716 票votes	1552.000 [1527.0, 1577.0]	17.00 · 不稳Volatile	—	—
9	9 - 22	claude-sonnet-4-6 Anthropic · Proprietary	1535±10.0	4.5K 票votes	1535.000 [1525.0, 1545.0]	13.00 · 不稳Volatile	$3 / $15	1M
10	12 - 25	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1522±14.0	3.0K 票votes	1522.000 [1508.0, 1536.0]	13.00 · 不稳Volatile	$5 / $25	200K
11	22 - 40	claude-opus-4-5-20251101 Anthropic · Proprietary	1472±12.0	3.5K 票votes	1472.000 [1460.0, 1484.0]	18.00 · 不稳Volatile	$5 / $25	200K
12	40 - 60	claude-opus-4-1-20250805 Anthropic · Proprietary	1415±17.0	2.1K 票votes	1415.000 [1398.0, 1432.0]	20.00 · 不稳Volatile	$15 / $75	200K
13	45 - 65	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1393±12.0	3.8K 票votes	1393.000 [1381.0, 1405.0]	20.00 · 不稳Volatile	$3 / $15	200K
14	45 - 66	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1389±12.0	4.4K 票votes	1389.000 [1377.0, 1401.0]	21.00 · 不稳Volatile	$3 / $15	200K
15	73 - 82	claude-haiku-4-5-20251001 Anthropic · Proprietary	1315±9.0	6.5K 票votes	1315.000 [1306.0, 1324.0]	9.00 · 波动Unstable	$1 / $5	200K

🔍

没有找到匹配的模型，换个关键词试试？No matching models found. Try a different keyword?