← Overall rankings

LMArena Vision arena · published July 12, 2026

Anthropic leads the LMArena vision arena.

As of July 12, 2026, Anthropic leads the LMArena vision arena with claude-fable-5 at 1335.1 across 4,383 battles, according to LMArena.

Current through July 12, 2026. 140 published snapshots. 113 of 143 models resolved (30 held for exact-match review).

LMArena vision arena rating, published July 12, 2026. Top 25 of 108 rows.
RankLMArena ratingOrganizationModelReported intervalGap to leaderBattles
011335.1AnthropicClaude Fable 51324.5 to 1345.8Leader4,383
021318.4Anthropicclaude-opus-4-7-thinking1311.4 to 1325.5-16.718,567
031316.5Anthropicclaude-opus-4-61309.8 to 1323.2-18.622,778
041315.5AnthropicClaude Opus 4.71308.5 to 1322.5-19.619,049
051315.0Anthropicclaude-opus-4-6-thinking1308.0 to 1322.0-20.118,430
061308.8Googlegemini-3.5-flash-medium1297.1 to 1320.5-26.33,350
071307.3MetaMuse Spark1297.8 to 1316.8-27.85,621
081304.9GoogleGemini 3 Pro1297.2 to 1312.5-30.213,117
091300.5Googlegemini-3.5-flash-high1288.2 to 1312.8-34.62,988
101298.8OpenAIgpt-5.4-high1291.8 to 1305.9-36.318,422
111296.7OpenAIgpt-5.5-high1289.3 to 1304.0-38.415,445
121295.5Googlegemini-3.1-pro-preview1289.6 to 1301.5-39.634,899
131295.4OpenAIgpt-5.51288.1 to 1302.7-39.716,562
141294.8Anthropicclaude-opus-4-8-thinking1286.3 to 1303.3-40.39,124
151291.3Anthropicclaude-opus-4-81282.7 to 1299.8-43.89,505
161290.6OpenAIgpt-5.41283.6 to 1297.7-44.518,333
171283.6Googlegemini-3-flash1277.9 to 1289.2-51.533,678
181282.7Moonshot AIkimi-k2.61275.4 to 1290.0-52.415,215
191282.4Anthropicclaude-sonnet-4-61275.9 to 1289.0-52.723,147
201275.5ByteDancedola-seed-2.0-pro1267.8 to 1283.2-59.610,345
211274.5Anthropicclaude-sonnet-5-high1263.8 to 1285.2-60.64,103
221272.2Alibabaqwen3.7-plus1262.6 to 1281.8-62.95,541
231269.9Googlegemma-4-31b1263.2 to 1276.6-65.231,087
241267.4OpenAIgpt-5.2-chat-latest-202602101260.5 to 1274.4-67.715,536
251266.7Alibabaqwen3.5-397b-a17b1260.4 to 1273.0-68.422,096

Frontier race

Category Kings: Vision arena frontier by organization

Anthropic holds the vision arena frontier at 1335 as of July 12, 2026.

Vision arena frontier ratings by organization over timeAnthropic holds the vision arena frontier at 1335 as of July 12, 2026. 9 organizations are tracked from June 29, 2024 to July 12, 2026.11101180125013202024-062024-112025-032025-072026-012026-07Anthropic 1335Google 1309Meta 1307OpenAI 1299Moonshot AI 1283ByteDance 1276Alibaba 1272xAI 1259Mistral AI 1225

Method: Frontier is the maximum resolved LMArena rating per organization on each publish date. Organizations limited to the union of the seven tracked homepage providers and organizations in the latest board top 25 by officialRank. Quarantined dates are excluded, and this category series keeps its own method epoch and is never joined to the legacy archive.

Vision arena frontier by organization: latest resolved score per organization, from the reviewed LMArena category artifact.
OrganizationLatest modelLatest LMArena ratingFirst tracked date
Anthropicanthropic/claude-fable-51335.1June 29, 2024
Googlegoogle/gemini-3.5-flash-medium1308.8June 29, 2024
Metameta/muse-spark1307.3May 11, 2025
OpenAIopenai/gpt-5.4-high1298.8June 29, 2024
Moonshot AImoonshot/kimi-k2.61282.7January 29, 2026
ByteDancebytedance/dola-seed-2.0-pro1275.5February 16, 2026
Alibabaalibaba/qwen3.7-plus1272.2September 30, 2025
xAIxai/grok-4.20-beta-0309-reasoning1259.3July 17, 2025
Mistral AImistral/mistral-large-31225.4June 24, 2025
Anthropic leads the vision arena frontier at 1335.1 on July 12, 2026. Frontier is the highest resolved score per organization per publish date. Quarantined dates are excluded and this category is never joined to the legacy archive.

Definitions

What these terms mean.

Vision arena
The LMArena vision arena, where models answer prompts that include image input. Model Gauntlet mirrors this named board and adds no separate vision test.
Frontier by organization
The highest resolved score for each organization on each publish date. It tracks how far each lab has pushed this category, not an average of all its models.
Confidence interval
The reported 95% range LMArena publishes with each rating. Overlapping intervals mean this snapshot does not separate those ranks decisively.

Vision arena questions

Which model leads the Vision arena right now?

According to the LMArena vision board published July 12, 2026, Anthropic leads with claude-fable-5 at 1335.1, across 4,383 battles. That is 16.7 points ahead of the next board entry inside this one snapshot.

Is this a Model Gauntlet vision ranking?

No. This board mirrors one named source, the LMArena vision arena, published July 12, 2026. Model Gauntlet publishes no composite or consensus score and runs no evaluation of its own.

How many models and organizations are in the vision board?

The reviewed artifact covers 143 models across 29 organizations, with 113 models resolved to exact identities and 30 held for review. The history spans 140 snapshots from June 29, 2024 to July 12, 2026.

Why do some scores have overlapping confidence intervals?

LMArena publishes a 95% confidence interval with each rating. Where two intervals overlap, this single snapshot does not separate those ranks decisively, so treat small vision gaps with caution.