LMArena Search leaderboard
- GPT-5.6 Sol leads
- 1261
- models measured
- 10
- lead over #2
- +0 Elo
- median
- 1230
Leader on LMArena Search · read October 22
On October 22, 2026, 10 of our catalog's models had a LMArena Search result, and OpenAI GPT-5.6 Sol led with 1261, ahead of Qwen3.8 Max (0902) at 1261.
Questions answered with web search, by models that search. People ask a question, compare two anonymous answers and vote for the better one; the rating is built from those votes, as LMArena publishes it.
Role in the index
LMArena Search is shown as published and does not feed any of our indexes. Read the methodology
| # | Model | Result | Votes | Interval (±) | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|---|
| 1 | GPT-5.6 SolOpenAI | 1261 | 60,437 | ±6.3 | 73.5 | $20.00 | |
| 2 | Qwen3.8 Max (0902)Qwen | 1261 | 1,870 | ±13.2 | 62.4 | $6.00 | |
| 3 | Claude Fable 5.1Anthropic | 1246 | 12,782 | ±7.0 | 84.2 | $50.00 | |
| 4 | Claude Opus 5Anthropic | 1242 | 13,285 | ±6.9 | 83.0 | $25.00 | |
| 5 | Claude Opus 4.7Anthropic | 1230 | 127,506 | ±4.9 | 67.5 | $25.00 | |
| 6 | Claude Fable 5Anthropic | 1229 | 73,596 | ±6.5 | 79.3 | $50.00 | |
| 7 | Grok 4.5xAI | 1216 | 76,458 | ±5.9 | 58.6 | $6.00 | |
| 8 | Claude Opus 5.5Anthropic | 1213 | 10,842 | ±7.1 | 88.8 | $20.00 | |
| 9 | Claude Opus 4.8Anthropic | 1204 | 106,304 | ±5.6 | 65.0 | $25.00 | |
| 10 | Grok 4.3xAI | 1166 | 128,393 | ±4.7 | 37.4 | $2.50 |
Only models in our catalog are listed, and each appears once with its best published run. 184 rows were read from the source on October 22, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.