LMArena Search arena · published July 12, 2026
Anthropic leads the LMArena search arena.
As of July 12, 2026, Anthropic leads the LMArena search arena with claude-opus-4-7 at 1234.9 across 62,037 battles, according to LMArena.
Current through July 12, 2026. 37 published snapshots. 7 of 32 models resolved (25 held for exact-match review).
| Rank | LMArena rating | Organization | Model | Reported interval | Gap to leader | Battles |
|---|---|---|---|---|---|---|
| 01 | 1234.9 | Anthropic | Claude Opus 4.7 | 1229.3 to 1240.4 | Leader | 62,037 |
| 02 | 1234.3 | Anthropic | Claude Fable 5 | 1226.3 to 1242.4 | -0.6 | 9,738 |
| 03 | 1227.0 | Baidu | ernie-5.1 | 1217.3 to 1236.7 | -7.9 | 3,809 |
| 04 | 1207.7 | Anthropic | claude-opus-4-8 | 1201.1 to 1214.3 | -27.2 | 42,126 |
| 05 | 1206.9 | xAI | grok-4.20-multi-agent-beta-0309 | 1201.6 to 1212.2 | -28.0 | 80,836 |
| 06 | 1189.5 | xAI | grok-4.20-beta1 | 1183.4 to 1195.5 | -45.4 | 53,904 |
| 07 | 1163.1 | xAI | grok-4.3 | 1157.8 to 1168.3 | -71.8 | 61,768 |
Frontier race
Category Kings: Search arena frontier by organization
Anthropic holds the search arena frontier at 1235 as of July 12, 2026.
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.
| Organization | Latest model | Latest LMArena rating | First tracked date |
|---|---|---|---|
| Anthropic | anthropic/claude-opus-4-7 | 1234.9 | April 27, 2026 |
| Baidu | baidu/ernie-5.1 | 1227.0 | May 8, 2026 |
| xAI | xai/grok-4.20-multi-agent-beta-0309 | 1206.9 | February 25, 2026 |
Definitions
What these terms mean.
- Search arena
- The LMArena search arena, where models answer prompts that require retrieval. It measures human preference on search-style prompts, not retrieval accuracy.
- 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.
Follow the evidence
Compare this board against the overall LMArena rankings, shortlist candidates with the Reasoning and research guide,read the Anthropic lab file, and see how rankings are selected. Model profiles on this board: Claude Opus 4.7, Claude Fable 5.
Search arena questions
Which model leads the Search arena right now?
According to the LMArena search board published July 12, 2026, Anthropic leads with claude-opus-4-7 at 1234.9, across 62,037 battles. That is 0.6 points ahead of the next board entry inside this one snapshot.
Is this a Model Gauntlet search ranking?
No. This board mirrors one named source, the LMArena search 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 search board?
The reviewed artifact covers 32 models across 9 organizations, with 7 models resolved to exact identities and 25 held for review. The history spans 37 snapshots from August 7, 2025 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 search gaps with caution.