LMArena Search Arena
LMArena · search-2026-08-24-51d09b2e834b · Blind human preferences for search-augmented responses in LMArena.
Model ranking
Publisher benchmark →Source | |||||||
|---|---|---|---|---|---|---|---|
| #1 | GPT-5.6 SolOpenAI | 1257.26 | — | 29,663 | gpt-5.6-sol-xhigh; 95% CI [1249.79496224, 1264.72573796]; votes 29663; rank 1unknown | Original sourcewinner eligible | Third-party benchmark |
| #2 | Claude Fable 5Anthropic | 1230.22 | — | 41,795 | claude-fable-5; 95% CI [1222.30895335, 1238.13609545]; votes 41795; rank 5unknown | Original sourcewinner eligible | Third-party benchmark |
2 models ranked by the best winner-eligible current-version score when available, otherwise the best publisher-artifact score; highest first. Observed Aug 29, 2026.
Ranking protocol
arena rating · rating. Each model appears once; verified winner-eligible runs take precedence, and missing models are not imputed.
Acquisition coverage
2 published models from 34 source rows; 32 source identities remain quarantined.
Primary evidence