Arena Search

Citation frequency 2/3
What does it measure?
Tests, through user votes, how good the answers are when a search-enabled AI replies to a question with citations.
Who evaluates it, and how?
A user asks a question; two anonymous search-enabled AIs answer with citations and the user votes for the better answer. The votes are fitted with a Bradley–Terry model, then converted to the Elo scale.
Reading the score
Scores are Elo ratings from head-to-head human votes. Higher is better. Citation formatting is standardized so the models cannot be recognized by style.
Top score1256
Models tested29
Scoring basisHigher is better
Last updated2026.11.19
Model release date

Which AI gives the search answers people prefer most?

Arena Search

  1. 🥇OpenAIGPT-5.6 Sol1256
  2. 🥈AnthropicClaude Opus 4.61252
  3. 🥉OpenAIGPT-5.51246
  4. #4AnthropicClaude Opus 5Reasoning effort: High1238
  5. #5AnthropicClaude Fable 5.1Reasoning effort: High1237
  6. #6OpenAIGPT-6 Astra1231
  7. #7AnthropicClaude Opus 4.71230
  8. #8OpenAIGPT-6.1 Sol1230
  9. #9AnthropicClaude Fable 51228
  10. #10AnthropicClaude Sonnet 4.61220
  11. #11SpaceXSIGrok 4.51216
  12. #12AnthropicClaude Opus 5.5Reasoning effort: Medium1214
  13. #13GoogleGemini 3.1 Pro1211
  14. #14AnthropicClaude Opus 4.81202
  15. #15OpenAIGPT-5.41198
  16. #16GoogleGemini 3 Flash1195
  17. #17OpenAIGPT-6.2 Astra1191
  18. #18SpaceXSIGrok 4.201191
  19. #19AnthropicClaude Sonnet 51187
  20. #20AnthropicClaude Opus 4.51179
  21. #21OpenAIGPT-6.2 Sol1179
  22. #22OpenAIGPT-6 Sol1174
  23. #23SpaceXSIGrok 4.31166
  24. #24AnthropicClaude Sonnet 4.51159
  25. #25OpenAIGPT-6 Luna1157
  26. #26AnthropicClaude Opus 4.11148
  27. #27GoogleGemini 2.5 Pro1143
  28. #28OpenAIGPT-51133
  29. #29AnthropicClaude Opus 41127
Top 3 within the margin of error · effectively tied · Half of models ≤ 1198

The "harness" is the agent program the AI used to carry out the task. The same model can score very differently depending on its harness and reasoning effort.