← Arena leaderboards

Search · Factuality

Arena · 40 models

RankModelScore
1gpt-5.6-sol-xhigh1,251.1262
2gpt-5.5-search1,247.3241
3qwen3.8-max1,240.4502
4gpt-6-astra-max1,239.9233
5gpt-6.1-sol-max1,236.13
6claude-opus-4-6-search1,226.8209
7gpt-5.2-search1,224.0059
8claude-fable-5.1-high1,221.5332
9grok-4.51,219.9155
10claude-opus-5-high1,216.8634
11ernie-5.11,213.7607
12gpt-5.4-search1,212.9434
13claude-fable-5-high1,212.3133
14claude-opus-4-71,210.1814
15claude-opus-5.5-medium1,205.1855
16gpt-5.1-search1,203.4798
17claude-sonnet-4-6-search1,201.7652
18gpt-5.2-search-non-reasoning1,197.96
19gpt-6-sol-max1,197.8531
20grok-4.20-multi-agent-beta-03091,197.7695
21claude-opus-4-81,197.2885
22gemini-3.1-pro-grounding1,196.9867
23grok-4.20-beta11,195.7695
24gemini-3-pro-grounding1,193.4495
25gpt-6-luna-max1,182.9992
26claude-sonnet-5-search1,181.7527
27claude-opus-4-5-search1,180.9084
28gemini-3-flash-grounding1,179.1309
29grok-4.31,174.991
30claude-sonnet-4-5-search1,162.4909
31gemini-2.5-pro-grounding1,162.4
32ppl-sonar-reasoning-pro-high1,155.5795
33claude-opus-4-1-search1,154.0945
34grok-4-1-fast-search1,152.0171
35grok-4-fast-search1,145.996
36gpt-5-search1,143.9698
37claude-opus-4-search1,139.6
38ppl-sonar-pro-high1,132.632
39grok-4-search1,131.1333
40o3-search1,129.2264