← Overall rankings

LMArena Document arena · published July 12, 2026

Anthropic leads the LMArena document arena.

As of July 12, 2026, Anthropic leads the LMArena document arena with claude-opus-4-6-thinking at 1508.1 across 24,188 battles, according to LMArena.

Current through July 12, 2026. 14 published snapshots. 34 of 34 models resolved (0 held for exact-match review).

LMArena document arena rating, published July 12, 2026. Top 25 of 32 rows.
RankLMArena ratingOrganizationModelReported intervalGap to leaderBattles
011508.1Anthropicclaude-opus-4-6-thinking1501.1 to 1515.0Leader24,188
021507.1AnthropicClaude Fable 51495.5 to 1518.7-1.02,644
031506.7Anthropicclaude-opus-4-61500.5 to 1512.9-1.436,602
041504.5Anthropicclaude-opus-4-7-thinking1497.7 to 1511.2-3.618,023
051501.2AnthropicClaude Opus 4.71494.7 to 1507.7-6.918,185
061488.2OpenAIgpt-5.5-high1481.4 to 1494.9-19.915,996
071485.9Anthropicclaude-sonnet-4-61479.9 to 1491.8-22.253,846
081480.6OpenAIgpt-5.51474.2 to 1487.1-27.516,410
091474.7Anthropicclaude-opus-4-8-thinking1466.9 to 1482.6-33.47,546
101472.2OpenAIgpt-5.41466.0 to 1478.5-35.928,910
111468.9Anthropicclaude-opus-4-81460.7 to 1477.2-39.27,298
121468.8Anthropicclaude-sonnet-5-high1457.4 to 1480.3-39.32,809
131462.2Googlegemini-3.5-flash-medium1450.6 to 1473.9-45.92,697
141461.4Anthropicclaude-opus-4-5-202511011451.1 to 1471.7-46.77,985
151449.2Moonshot AIkimi-k2.61441.6 to 1456.8-58.911,094
161445.8Anthropicclaude-sonnet-4-5-202509291439.4 to 1452.2-62.327,977
171444.9MetaMuse Spark1426.8 to 1463.0-63.21,086
181444.2Alibabaqwen3.7-plus1433.0 to 1455.3-63.92,700
191441.4Googlegemini-3.1-pro-preview1436.0 to 1446.8-66.744,046
201435.4MiniMaxminimax-m31427.1 to 1443.6-72.76,328
211433.6GoogleGemini 3 Pro1424.8 to 1442.4-74.510,748
221430.6Moonshot AIkimi-k2.5-thinking1423.8 to 1437.3-77.519,342
231424.2Googlegemma-4-31b1416.1 to 1432.4-83.910,132
241421.7Googlegemini-2.5-pro1415.5 to 1427.9-86.425,053
251420.9Anthropicclaude-haiku-4-5-202510011414.8 to 1427.0-87.230,187

Frontier race

Category Kings: Document arena frontier by organization

Anthropic holds the document arena frontier at 1508 as of July 12, 2026.

Document arena frontier ratings by organization over timeAnthropic holds the document arena frontier at 1508 as of July 12, 2026. 8 organizations are tracked from March 3, 2026 to July 12, 2026.13901430147015102026-032026-042026-042026-052026-062026-07Anthropic 1508OpenAI 1488Google 1462Moonshot AI 1449Meta 1445Alibaba 1444MiniMax 1435xAI 1413

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.

Document arena frontier by organization: latest resolved score per organization, from the reviewed LMArena category artifact.
OrganizationLatest modelLatest LMArena ratingFirst tracked date
Anthropicanthropic/claude-opus-4-6-thinking1508.1March 3, 2026
OpenAIopenai/gpt-5.5-high1488.2March 3, 2026
Googlegoogle/gemini-3.5-flash-medium1462.2March 3, 2026
Moonshot AImoonshot/kimi-k2.61449.2April 14, 2026
Metameta/muse-spark1444.9April 19, 2026
Alibabaalibaba/qwen3.7-plus1444.2July 2, 2026
MiniMaxminimax/minimax-m31435.4June 3, 2026
xAIxai/grok-4.20-beta-0309-reasoning1413.1April 14, 2026
Anthropic leads the document arena frontier at 1508.1 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.

Document arena
The LMArena document arena, where models answer prompts grounded in document input. Model Gauntlet mirrors this named board without adding its own document 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.

Document arena questions

Which model leads the Document arena right now?

According to the LMArena document board published July 12, 2026, Anthropic leads with claude-opus-4-6-thinking at 1508.1, across 24,188 battles. That is 1.0 points ahead of the next board entry inside this one snapshot.

Is this a Model Gauntlet document ranking?

No. This board mirrors one named source, the LMArena document 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 document board?

The reviewed artifact covers 34 models across 9 organizations, with 34 models resolved to exact identities and 0 held for review. The history spans 14 snapshots from March 3, 2026 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 document gaps with caution.