BenchmarksChat preference
Search Arena
A crowdsourced human-preference leaderboard from LMArena that ranks search-augmented LLMs via blind pairwise votes on grounded, web-search answers, reported as Bradley-Terry Elo-scale ratings.
Chat preferenceEloHigher is better
What is Search Arena?
A crowdsourced human-preference leaderboard from LMArena that ranks search-augmented LLMs via blind pairwise votes on grounded, web-search answers, reported as Bradley-Terry Elo-scale ratings. evals.report tracks reported Search Arena scores with the model, source, status, date, and run caveats attached — official leaderboard scores, vendor-reported launches, and clearly labeled community runs.
Top reported Search Arena score: Claude Opus 4.6 — 1251 (Elo).
| Model | Lab | Score↓ | Source model | Status | Date | |
|---|---|---|---|---|---|---|
| Claude Opus 4.6 | Anthropic | 1251 | — | Verified | Feb 5, 2026 | Details |
| GPT-5.5 | OpenAI | 1239 | — | Verified | Apr 23, 2026 | Details |
| Claude Opus 4.7 | Anthropic | 1237 | — | Verified | Apr 16, 2026 | Details |
| ERNIE 5.1 | Baidu | 1226 | — | Verified | May 8, 2026 | Details |
| Claude Sonnet 4.6 | Anthropic | 1219 | — | Verified | Feb 17, 2026 | Details |
| Gemini 3.1 Pro Preview | Google DeepMind | 1216 | — | Verified | Feb 19, 2026 | Details |
| GPT-5.2 | OpenAI | 1210 | — | Verified | Dec 11, 2025 | Details |
| Gemini 3 Pro | Google DeepMind | 1208 | — | Verified | Nov 18, 2025 | Details |
| Gemini 3 Flash | Google DeepMind | 1206 | — | Verified | Dec 17, 2025 | Details |
| GPT-5.1 | OpenAI | 1199 | — | Verified | Nov 12, 2025 | Details |
| GPT-5.4 | OpenAI | 1199 | — | Verified | Mar 5, 2026 | Details |
| Grok 4.20 beta reasoning | xAI | 1193 | — | Verified | Mar 9, 2026 | Details |
| Grok 4.3 | xAI | 1189 | — | Verified | Apr 17, 2026 | Details |
| Claude Opus 4.5 | Anthropic | 1182 | — | Verified | Nov 24, 2025 | Details |
| Grok 4.1 fast reasoning | xAI | 1175 | — | Verified | Nov 19, 2025 | Details |
| Claude Sonnet 4.5 | Anthropic | 1152 | — | Verified | Sep 29, 2025 | Details |
| Claude Opus 4.1 | Anthropic | 1148 | — | Verified | Aug 5, 2025 | Details |
| o3 | OpenAI | 1144 | — | Verified | Apr 16, 2025 | Details |
| Gemini 2.5 Pro | Google DeepMind | 1143 | — | Verified | Mar 25, 2025 | Details |
| Grok 4 | xAI | 1143 | — | Verified | Jul 9, 2025 | Details |
| GPT-5 | OpenAI | 1134 | — | Verified | Aug 7, 2025 | Details |
| Claude Opus 4 | Anthropic | 1128 | — | Verified | May 22, 2025 | Details |
| GPT-4o | OpenAI | 1006 | — | Verified | May 13, 2024 | Details |
Each row reports the model’s Elo on Search Arena. Click a row for the full run context.