← Overall rankings

LMArena Coding arena · published July 20, 2026

Anthropic leads the LMArena coding arena.

As of July 20, 2026, Anthropic leads the LMArena coding arena with claude-opus-4-7-thinking at 1553.0 across 14,244 battles, according to LMArena.

Current through July 20, 2026. 165 published snapshots. 380 of 384 models resolved (4 held for exact-match review).

LMArena coding arena rating, published July 20, 2026. Top 25 of 322 rows.
RankLMArena ratingOrganizationModelReported intervalGap to leaderBattles
011553.0Anthropicclaude-opus-4-7-thinking1546.4 to 1559.6Leader14,244
021550.1Anthropicclaude-opus-4-6-thinking1543.9 to 1556.2-2.916,120
031548.7AnthropicClaude Opus 4.71542.2 to 1555.2-4.314,491
041547.7AnthropicClaude Fable 51535.9 to 1559.6-5.32,725
051547.6Anthropicclaude-opus-4-61541.8 to 1553.5-5.418,333
061535.1Anthropicclaude-opus-4-8-thinking1527.3 to 1542.9-17.98,366
071533.0Metamuse-spark-1.11519.5 to 1546.5-20.02,087
081530.7Anthropicclaude-opus-4-81522.9 to 1538.5-22.38,589
091530.3Anthropicclaude-opus-4-5-20251101-thinking-32k1522.9 to 1537.6-22.77,621
101527.4Anthropicclaude-sonnet-4-61521.2 to 1533.6-25.615,590
111526.3Alibabaqwen3.7-max-preview1507.9 to 1544.8-26.71,123
121526.1OpenAIgpt-5.6-sol-xhigh1510.5 to 1541.7-26.91,550
131525.0MetaMuse Spark1514.8 to 1535.2-28.03,777
141523.6Anthropicclaude-sonnet-5-high1513.0 to 1534.1-29.43,543
151522.7Anthropicclaude-opus-4-5-202511011517.1 to 1528.2-30.317,316
161521.1Googlegemini-3.1-pro-preview1515.7 to 1526.6-31.922,888
171521.0OpenAIgpt-5.4-high1514.8 to 1527.1-32.015,756
181520.5Z.aiglm-5.11513.1 to 1527.9-32.58,422
191519.8Anthropicclaude-sonnet-4-5-20250929-thinking-32k1514.8 to 1524.8-33.219,300
201519.6xAIgrok-4.51506.1 to 1533.2-33.42,076
211519.3OpenAIgpt-5.5-high1512.4 to 1526.1-33.712,460
221518.8Xiaomimimo-v2.5-pro1511.7 to 1525.9-34.211,355
231518.7GoogleGemini 3 Pro1511.6 to 1525.8-34.38,576
241515.4OpenAIgpt-5.2-chat-latest-202602101508.4 to 1522.4-37.69,160
251514.9Moonshot AIkimi-k2.61507.7 to 1522.0-38.110,419

Frontier race

Category Kings: Coding arena frontier by organization

Anthropic holds the coding arena frontier at 1553 as of July 20, 2026.

Coding arena frontier ratings by organization over timeAnthropic holds the coding arena frontier at 1553 as of July 20, 2026. 11 organizations are tracked from September 15, 2024 to July 20, 2026.11401260138015002024-092025-022025-072025-122026-032026-07Anthropic 1553Meta 1533Alibaba 1526OpenAI 1526Google 1521Z.ai 1521xAI 1520Xiaomi 1519Moonshot AI 1515DeepSeek 1501Mistral AI 1479

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.

Coding arena frontier by organization: latest resolved score per organization, from the reviewed LMArena category artifact.
OrganizationLatest modelLatest LMArena ratingFirst tracked date
Anthropicanthropic/claude-opus-4-7-thinking1553.0September 15, 2024
Metameta/muse-spark-1.11533.0September 15, 2024
Alibabaalibaba/qwen3.7-max-preview1526.3September 15, 2024
OpenAIopenai/gpt-5.6-sol-xhigh1526.1September 15, 2024
Googlegoogle/gemini-3.1-pro-preview1521.1September 15, 2024
Z.aizai/glm-5.11520.5September 15, 2024
xAIxai/grok-4.51519.6September 15, 2024
Xiaomixiaomi/mimo-v2.5-pro1518.8December 23, 2025
Moonshot AImoonshot/kimi-k2.61514.9July 17, 2025
DeepSeekdeepseek/deepseek-v4-pro1501.4September 15, 2024
Mistral AImistral/mistral-medium-3.51479.1September 15, 2024
Anthropic leads the coding arena frontier at 1553.0 on July 20, 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.

Coding arena
The LMArena style-controlled text battles filtered to prompts categorized as coding. Model Gauntlet mirrors this named subset and does not run code evaluations itself.
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.

Other coding boards

Aider polyglot mirrors a different coding subject.

The Aider polyglot leaderboard ranks full model-and-editor-system configurations on code editing, not bare models. A resolved entry names only the model portion of a system configuration, so it is never a bare-model score and is not comparable to this LMArena coding arena. It appears as its own labeled column with attribution.

See the Aider polyglot column →

Coding arena questions

Which model leads the Coding arena right now?

According to the LMArena coding board published July 20, 2026, Anthropic leads with claude-opus-4-7-thinking at 1553.0, across 14,244 battles. That is 2.9 points ahead of the next board entry inside this one snapshot.

Is this a Model Gauntlet coding ranking?

No. This board mirrors one named source, the LMArena coding arena, published July 20, 2026. Model Gauntlet publishes no composite or consensus score and runs no evaluation of its own.

How many models and organizations are in the coding board?

The reviewed artifact covers 384 models across 61 organizations, with 380 models resolved to exact identities and 4 held for review. The history spans 165 snapshots from September 15, 2024 to July 20, 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 coding gaps with caution.