Name: 视觉理解模型厂商排行榜（2024-07-16）- 最佳图像与多模态模型 - 厂商聚合排名
Creator: LM Arena
License: https://creativecommons.org/licenses/by/4.0/
Keywords: AI 视觉理解模型排行榜,视觉 AI 排行榜,最佳图像与多模态模型,AI 模型排行,Elo 积分,厂商排名,Labs

视觉模型 Arena 榜单LM Arena Global AI Leaderboard🏆综合榜单🏆Overall

查看能够对图像、图表、OCR 等视觉输入进行推理的多模态 AI 模型的综合 Elo 积分排名，数据来源于真实用户匿名盲测投票。Explore Elo rankings of multimodal AI models that reason about images, charts, and OCR inputs — rated by real anonymous user votes.

2024-07-16

▾

上榜模型Models

参赛厂商Providers

69.0K

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
🥇	76 - 127	OpenAI 最高得分模型Top Model: gpt-4o-2024-05-13	1221±5.3	7.7K 票votes	1220.557 [1215.3, 1225.9]	9.52 · 波动Unstable	$5 / $15	128K
🥈	86 - 139	Anthropic 最高得分模型Top Model: claude-3-5-sonnet-20240620	1208±5.1	10.2K 票votes	1207.684 [1203.4, 1213.6]	7.95 · 波动Unstable	$3 / $15	200K
🥉	—	Google 最高得分模型Top Model: gemini-1.5-pro-api-0514	1163±6.5	7.5K 票votes	1163.081 [1156.7, 1169.6]	12.14 · 不稳Volatile	—	—
4	76 - 88	LLaVA 最高得分模型Top Model: llava-v1.6-34b	1008±7.3	4.7K 票votes	1007.596 [999.0, 1013.6]	13.62 · 不稳Volatile	N/A	N/A
5	115 - 121	智谱 AI 最高得分模型Top Model: cogvlm2-llama3-chat-19b	996±11.9	2.0K 票votes	995.827 [982.2, 1006.0]	41.53 · 不稳Volatile	N/A	N/A

🔍

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