Name: Google WebDev 综合模型排行榜（2026-10-23） | AITNT
Creator: LM Arena
License: https://creativecommons.org/licenses/by/4.0/
Keywords: Google,WebDev综合,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 LeaderboardWebDev综合🏆Overall

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。

2026-10-23

▾

上榜模型Models

参赛厂商Providers

27.7K

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
🥇	8 - 17	Gemini 4 Argon (High) Google · Proprietary	1674±13.0	0 票votes	1674.000 [1661.0, 1687.0]	9.00 · 波动Unstable	—	—
🥈	32 - 39	Gemini 3.7 Flash (High) Google · Proprietary	1590±7.0Preliminary	0 票votes	1590.000 [1583.0, 1597.0]	7.00 · 波动Unstable	—	—
🥉	32 - 39	Gemini 3.8 Flash (High) Google · Proprietary	1585±7.0Preliminary	0 票votes	1585.000 [1578.0, 1592.0]	7.00 · 波动Unstable	—	—
4	45 - 53	Gemini 3.6 Flash (High) Google · Proprietary	1538±7.0	0 票votes	1538.000 [1531.0, 1545.0]	8.00 · 波动Unstable	—	—
5	53 - 70	gemini-3.5-flash Google · Proprietary	1503±15.0Preliminary	0 票votes	1503.000 [1488.0, 1518.0]	17.00 · 不稳Volatile	—	—
6	60 - 69	Gemini 3.5 Flash (High) Google · Proprietary	1499±7.0	0 票votes	1499.000 [1492.0, 1506.0]	9.00 · 波动Unstable	—	—
7	63 - 71	Gemini 3.5 Flash (Medium) Google · Proprietary	1491±7.0	0 票votes	1491.000 [1484.0, 1498.0]	8.00 · 波动Unstable	—	—
8	76 - 89	Gemini 3.1 Pro Preview Google · Proprietary	1447±5.0	0 票votes	1447.000 [1442.0, 1452.0]	13.00 · 不稳Volatile	—	—
9	77 - 92	Gemini 3 Pro Google · Proprietary	1440±8.0	14.1K 票votes	1440.000 [1432.0, 1448.0]	15.00 · 不稳Volatile	—	—
10	77 - 92	Gemini 3 Flash Google · Proprietary	1440±9.0	10.9K 票votes	1440.000 [1431.0, 1449.0]	15.00 · 不稳Volatile	—	—
11	70 - 107	Gemini 3.5 Flash-Lite Google · Proprietary	1434±41.0	0 票votes	1434.000 [1393.0, 1475.0]	37.00 · 不稳Volatile	—	—
12	101 - 112	Gemini 3 Flash (Minimal) Google · Proprietary	1385±5.0	0 票votes	1385.000 [1380.0, 1390.0]	11.00 · 波动Unstable	—	—
13	110 - 120	Gemma 4 31B Google · Apache 2.0	1368±6.0	0 票votes	1368.000 [1362.0, 1374.0]	10.00 · 波动Unstable	—	—
14	109 - 125	Gemma 4 26B A4B Google · Apache 2.0	1360±17.0	0 票votes	1360.000 [1343.0, 1377.0]	16.00 · 不稳Volatile	—	—
15	134 - 143	Gemini 3.1 Flash-Lite Preview Google · Proprietary	1256±7.0	0 票votes	1256.000 [1249.0, 1263.0]	9.00 · 波动Unstable	—	—
16	137 - 147	Gemini 2.5 Pro Google · Proprietary	1226±16.0	2.7K 票votes	1226.000 [1210.0, 1242.0]	10.00 · 波动Unstable	—	—

🔍

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