All rankings / Search and documents

Search

Human preference ratings for the overall category of this Arena task. Scores from different boards are not interchangeable.

42 entries · Arena score · Higher is better

Source publication: 2026-10-13. Retrieved 2026-11-05.

Source: Arena (lmarena-ai) · CC-BY-4.0.

Ranks use confidence bounds. Several models can share a rank; the rows within a shared rank are displayed by score.

Search · Arena score
Significance rankModel / evaluated variantArena score95% confidence intervalVotes
1gpt-5.6-sol-xhighopenai1,261.131,254.84 – 1,267.4260,437
1qwen3.8-maxalibaba1,261.081,247.89 – 1,274.261,870
1claude-opus-4-6-searchanthropic1,251.371,246.83 – 1,255.91173,191
2gpt-5.5-searchopenai1,246.551,241.65 – 1,251.45125,957
2claude-fable-5.1-highanthropic1,245.851,238.79 – 1,252.912,782
2claude-opus-5-highanthropic1,241.571,234.7 – 1,248.4413,285
5gpt-6-astra-maxopenai1,233.621,225.77 – 1,241.4618,483
4gpt-6.1-sol-maxopenai1,233.11,224.24 – 1,241.965,555
6claude-opus-4-7anthropic1,230.151,225.28 – 1,235.01127,506
6claude-fable-5-highanthropic1,229.141,222.63 – 1,235.6573,596
6ernie-5.1baidu1,226.721,217.24 – 1,236.194,024
9claude-sonnet-4-6-searchanthropic1,220.51,216.03 – 1,224.98173,986
11grok-4.5xai1,215.941,210.08 – 1,221.7976,458
11claude-opus-5.5-mediumanthropic1,212.751,205.66 – 1,219.8410,842
13gemini-3.1-pro-groundinggoogle1,208.811,204.13 – 1,213.48151,436
13gpt-5.2-searchopenai1,207.241,201.7 – 1,212.7855,634
13gemini-3-pro-groundinggoogle1,206.471,201 – 1,211.9338,857
13grok-4.20-multi-agent-beta-0309xai1,204.81,199.36 – 1,210.24126,238
14claude-opus-4-8anthropic1,204.111,198.49 – 1,209.73106,304
15gpt-5.1-searchopenai1,199.71,194.51 – 1,204.8963,042
15gpt-5.4-searchopenai1,199.081,193.6 – 1,204.57126,730
18gemini-3-flash-groundinggoogle1,195.691,191.39 – 1,200196,399
20claude-sonnet-5-searchanthropic1,190.941,184.78 – 1,197.172,978
20grok-4.20-beta1xai1,190.481,184.5 – 1,196.4557,049
23claude-opus-4-5-searchanthropic1,179.581,173.99 – 1,185.1865,047
25gpt-6-sol-maxopenai1,174.911,167.84 – 1,181.9911,313
25gpt-5.2-search-non-reasoningopenai1,171.461,165.95 – 1,176.9879,796
25grok-4-1-fast-searchxai1,170.921,165.96 – 1,175.8785,919
25grok-4-fast-searchxai1,170.11,165.47 – 1,174.7243,083
26grok-4.3xai1,165.811,161.07 – 1,170.54128,393
30claude-sonnet-4-5-searchanthropic1,160.271,155.15 – 1,165.39144,153
27gpt-6-luna-maxopenai1,159.561,152.33 – 1,166.7810,793
32claude-opus-4-1-searchanthropic1,148.451,143.58 – 1,153.3179,806
33o3-searchopenai1,144.851,139.25 – 1,150.4420,770
33gemini-2.5-pro-groundinggoogle1,142.81,138.12 – 1,147.4786,689
33grok-4-searchxai1,141.861,135.77 – 1,147.9519,195
33ppl-sonar-reasoning-pro-highperplexity1,139.011,133.19 – 1,144.8229,439
34gpt-5-searchopenai1,133.491,127.51 – 1,139.4720,865
36ppl-sonar-pro-highperplexity1,130.281,124.47 – 1,136.0828,899
38claude-opus-4-searchanthropic1,127.431,122.02 – 1,132.8431,506
41diffbot-small-xldiffbot1,022.671,014.16 – 1,031.176,368
41api-gpt-4o-searchopenai1,006.58995.37 – 1,017.793,399

What this ranking can tell you

  • The population is the models in this source board, including variants and models without an available API price.
  • Ranks use the published confidence bounds: one plus the number of models whose lower bound exceeds this model’s upper bound. Shared ranks are not proof of equal performance.

Check the source

The original evidence is retained byte for byte. The downloadable board includes the source URLs, revision and SHA-256 hashes.

Download this board and provenance →

Source files and licences

Explore other model types →Read the benchmark guide →

Evidence & Ask