Arena Search Overall — 25% Factuality
Search · 2026-07-15
Arena's Search rating with the site's default 25% factuality adjustment applied to the overall raw leaderboard. It is kept separate because factuality weighting changes both ratings and ranks.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 1251 |
| GPT-6 Astra | 1240 |
| GPT-6.1 Sol | 1236 |
| Claude Fable 5.1 | 1222 |
| Grok 4.5 | 1220 |
| Claude Opus 5 | 1217 |
| ERNIE 5.1 | 1214 |
| Claude Fable 5 | 1212 |
| Opus 4.7 | 1210 |
| Claude Opus 5.5 | 1205 |
| GPT-6 Sol | 1198 |
| Opus 4.8 | 1197 |
| GPT-6 Luna | 1183 |
| Gemini 3 Flash Preview | 1179 |
| Grok 4.3 | 1175 |
| Grok 4 Fast | 1146 |
| GPT-5 | 1144 |