Name: Anthropic 英语高难度提示词评测模型排行榜（2026-08-22） | AITNT
Creator: LM Arena
License: https://creativecommons.org/licenses/by/4.0/
Keywords: Anthropic,困难(英语),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困难(英语)🧠Hard (English)

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。

2026-08-22

▾

上榜模型Models

参赛厂商Providers

474.0K

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
🥇	1 - 5	claude-opus-4-6-high Anthropic · Proprietary	1537±5.0	21.6K 票votes	1537.000 [1532.0, 1542.0]	4.00 · 稳定Stable	—	—
🥈	1 - 8	claude-fable-5 Anthropic · Proprietary	1533±8.0	7.1K 票votes	1533.000 [1525.0, 1541.0]	7.00 · 波动Unstable	—	—
🥉	1 - 8	claude-opus-4-6 Anthropic · Proprietary	1530±5.0	23.7K 票votes	1530.000 [1525.0, 1535.0]	7.00 · 波动Unstable	$5 / $25	1M
4	1 - 9	claude-opus-4-7-high Anthropic · Proprietary	1527±6.0	19.5K 票votes	1527.000 [1521.0, 1533.0]	8.00 · 波动Unstable	—	—
5	2 - 14	claude-opus-4-7 Anthropic · Proprietary	1521±6.0	19.7K 票votes	1521.000 [1515.0, 1527.0]	12.00 · 不稳Volatile	$5 / $25	1M
6	4 - 22	claude-opus-5-high Anthropic · Proprietary	1516±8.0	7.5K 票votes	1516.000 [1508.0, 1524.0]	18.00 · 不稳Volatile	—	—
7	5 - 23	claude-opus-4-8-high Anthropic · Proprietary	1514±6.0	13.6K 票votes	1514.000 [1508.0, 1520.0]	18.00 · 不稳Volatile	—	—
8	5 - 40	claude-opus-5-max Anthropic · Proprietary	1508±11.0	3.6K 票votes	1508.000 [1497.0, 1519.0]	35.00 · 不稳Volatile	—	—
9	6 - 32	claude-sonnet-4-6 Anthropic · Proprietary	1507±6.0	20.7K 票votes	1507.000 [1501.0, 1513.0]	26.00 · 不稳Volatile	$3 / $15	1M
10	6 - 35	claude-opus-4-8 Anthropic · Proprietary	1505±6.0	14.1K 票votes	1505.000 [1499.0, 1511.0]	29.00 · 不稳Volatile	—	—
11	6 - 38	claude-opus-4-5-20251101-high-32k Anthropic · Proprietary	1505±7.0	9.5K 票votes	1505.000 [1498.0, 1512.0]	32.00 · 不稳Volatile	—	—
12	9 - 51	claude-opus-4-5-20251101 Anthropic · Proprietary	1499±5.0	20.3K 票votes	1499.000 [1494.0, 1504.0]	42.00 · 不稳Volatile	$5 / $25	200K
13	9 - 52	claude-sonnet-4-5-20250929-high-32k Anthropic · Proprietary	1497±5.0	23.2K 票votes	1497.000 [1492.0, 1502.0]	43.00 · 不稳Volatile	—	—
14	9 - 57	claude-sonnet-5-high Anthropic · Proprietary	1497±7.0	8.0K 票votes	1497.000 [1490.0, 1504.0]	48.00 · 不稳Volatile	—	—
15	21 - 64	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1490±5.0	23.4K 票votes	1490.000 [1485.0, 1495.0]	43.00 · 不稳Volatile	$3 / $15	200K
16	21 - 72	claude-opus-4-1-20250805-thinking-16k Anthropic · Proprietary	1488±6.0	12.6K 票votes	1488.000 [1482.0, 1494.0]	51.00 · 不稳Volatile	$15 / $75	200K
17	31 - 76	claude-opus-4-1-20250805 Anthropic · Proprietary	1482±5.0	19.6K 票votes	1482.000 [1477.0, 1487.0]	45.00 · 不稳Volatile	$15 / $75	200K
18	62 - 112	claude-opus-4-20250514-thinking-16k Anthropic · Proprietary	1463±7.0	8.5K 票votes	1463.000 [1456.0, 1470.0]	50.00 · 不稳Volatile	$15 / $75	200K
19	75 - 120	claude-haiku-4-5-20251001 Anthropic · Proprietary	1456±4.0	36.0K 票votes	1456.000 [1452.0, 1460.0]	45.00 · 不稳Volatile	$1 / $5	200K
20	84 - 138	claude-sonnet-4-20250514-thinking-32k Anthropic · Proprietary	1448±7.0	8.2K 票votes	1448.000 [1441.0, 1455.0]	54.00 · 不稳Volatile	$3 / $15	1M
21	98 - 144	claude-opus-4-20250514 Anthropic · Proprietary	1443±7.0	10.0K 票votes	1443.000 [1436.0, 1450.0]	46.00 · 不稳Volatile	$15 / $75	200K
22	114 - 169	claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary	1429±7.0	7.8K 票votes	1429.000 [1422.0, 1436.0]	55.00 · 不稳Volatile	$3 / $15	200K
23	122 - 172	claude-sonnet-4-20250514 Anthropic · Proprietary	1424±7.0	9.3K 票votes	1424.000 [1417.0, 1431.0]	50.00 · 不稳Volatile	$3 / $15	1M
24	155 - 195	claude-3-7-sonnet-20250219 Anthropic · Proprietary	1406±7.0	8.9K 票votes	1406.000 [1399.0, 1413.0]	40.00 · 不稳Volatile	$3 / $15	200K
25	160 - 193	claude-3-5-sonnet-20241022 Anthropic · Proprietary	1406±5.0	15.8K 票votes	1406.000 [1401.0, 1411.0]	33.00 · 不稳Volatile	$3 / $15	200K
26	194 - 230	claude-3-5-sonnet-20240620 Anthropic · Proprietary	1368±7.0	14.3K 票votes	1368.000 [1361.0, 1375.0]	36.00 · 不稳Volatile	$3 / $15	200K
27	204 - 243	claude-3-5-haiku-20241022 Anthropic · Proprietary	1357±6.0	13.5K 票votes	1357.000 [1351.0, 1363.0]	39.00 · 不稳Volatile	$0.80 / $4	200K
28	233 - 273	claude-3-opus-20240229 Anthropic · Proprietary	1327±6.0	34.3K 票votes	1327.000 [1321.0, 1333.0]	40.00 · 不稳Volatile	$15 / $75	200K
29	276 - 298	claude-3-sonnet-20240229 Anthropic · Proprietary	1286±7.0	19.2K 票votes	1286.000 [1279.0, 1293.0]	22.00 · 不稳Volatile	$3 / $15	200K
30	283 - 308	claude-3-haiku-20240307 Anthropic · Proprietary	1270±7.0	20.7K 票votes	1270.000 [1263.0, 1277.0]	25.00 · 不稳Volatile	$0.25 / $1.25	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?