Name: Google 幽默理解模型排行榜（2026-06-03） | AITNT
Creator: LM Arena
License: https://creativecommons.org/licenses/by/4.0/
Keywords: Google,幽默理解,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幽默理解😆Humor

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。

2026-06-03

▾

上榜模型Models

参赛厂商Providers

13.5K

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 - 12	gemini-3-pro Google · Proprietary	1316±25.0	564 票votes	1316.000 [1291.0, 1341.0]	11.00 · 波动Unstable	$2 / $12	1M
🥈	1 - 14	gemini-3.1-pro-preview Google · Proprietary	1307±21.0	895 票votes	1307.000 [1286.0, 1328.0]	13.00 · 不稳Volatile	$2 / $12	1M
🥉	3 - 37	gemini-3-flash Google · Proprietary	1265±20.0	905 票votes	1265.000 [1245.0, 1285.0]	34.00 · 不稳Volatile	$0.50 / $3	1M
4	5 - 38	gemini-3.1-flash-lite-preview Google · Proprietary	1255±23.0	652 票votes	1255.000 [1232.0, 1278.0]	33.00 · 不稳Volatile	$0.25 / $1.50	1M
5	6 - 38	gemma-4-31b Google · Apache 2.0	1253±20.0	964 票votes	1253.000 [1233.0, 1273.0]	32.00 · 不稳Volatile	$0.14 / $0.40	262.1K
6	7 - 40	gemini-3-flash (thinking-minimal) Google · Proprietary	1245±20.0	851 票votes	1245.000 [1225.0, 1265.0]	33.00 · 不稳Volatile	$0.50 / $3	1M
7	8 - 39	gemini-2.5-pro Google · Proprietary	1243±14.0	3.1K 票votes	1243.000 [1229.0, 1257.0]	31.00 · 不稳Volatile	$1.25 / $10	1M
8	6 - 42	gemma-4-26b-a4b Google · Apache 2.0	1243±24.0	616 票votes	1243.000 [1219.0, 1267.0]	36.00 · 不稳Volatile	N/A	N/A
9	8 - 51	gemini-2.5-flash-preview-09-2025 Google · Proprietary	1226±37.0	216 票votes	1226.000 [1189.0, 1263.0]	43.00 · 不稳Volatile	$0.30 / $2.50	1M
10	22 - 50	gemini-2.5-flash Google · Proprietary	1206±15.0	2.1K 票votes	1206.000 [1191.0, 1221.0]	28.00 · 不稳Volatile	$0.30 / $2.50	1M
11	27 - 55	gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary	1188±19.0	1.4K 票votes	1188.000 [1169.0, 1207.0]	28.00 · 不稳Volatile	$0.10 / $0.40	1M
12	27 - 63	gemini-2.0-flash-001 Google · Proprietary	1168±41.0	228 票votes	1168.000 [1127.0, 1209.0]	36.00 · 不稳Volatile	$0.10 / $0.40	1M
13	43 - 63	gemma-3-27b-it Google · Gemma	1150±23.0	781 票votes	1150.000 [1127.0, 1173.0]	20.00 · 不稳Volatile	$0.08 / $0.16	131.1K
14	43 - 63	gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary	1136±37.0	214 票votes	1136.000 [1099.0, 1173.0]	20.00 · 不稳Volatile	$0.10 / $0.40	1M

🔍

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