---
title: "Search: model rankings and source evidence · Undominated.ai"
canonical: https://undominated.ai/rankings/arena-search/
description: "Search ranked by Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence."
---

# Search: model rankings and source evidence · Undominated.ai

> Search ranked by Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence.

[All rankings](/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)](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) · [CC-BY-4.0](https://creativecommons.org/licenses/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 rank | Model / evaluated variant | Arena score | 95% confidence interval | Votes |
| --- | --- | --- | --- | --- |
| 1 | gpt-5.6-sol-xhigh openai | 1,261.13 | 1,254.84 – 1,267.42 | 60,437 |
| 1 | qwen3.8-max alibaba | 1,261.08 | 1,247.89 – 1,274.26 | 1,870 |
| 1 | claude-opus-4-6-search anthropic | 1,251.37 | 1,246.83 – 1,255.91 | 173,191 |
| 2 | gpt-5.5-search openai | 1,246.55 | 1,241.65 – 1,251.45 | 125,957 |
| 2 | claude-fable-5.1-high anthropic | 1,245.85 | 1,238.79 – 1,252.9 | 12,782 |
| 2 | claude-opus-5-high anthropic | 1,241.57 | 1,234.7 – 1,248.44 | 13,285 |
| 5 | gpt-6-astra-max openai | 1,233.62 | 1,225.77 – 1,241.46 | 18,483 |
| 4 | gpt-6.1-sol-max openai | 1,233.1 | 1,224.24 – 1,241.96 | 5,555 |
| 6 | claude-opus-4-7 anthropic | 1,230.15 | 1,225.28 – 1,235.01 | 127,506 |
| 6 | claude-fable-5-high anthropic | 1,229.14 | 1,222.63 – 1,235.65 | 73,596 |
| 6 | ernie-5.1 baidu | 1,226.72 | 1,217.24 – 1,236.19 | 4,024 |
| 9 | claude-sonnet-4-6-search anthropic | 1,220.5 | 1,216.03 – 1,224.98 | 173,986 |
| 11 | grok-4.5 xai | 1,215.94 | 1,210.08 – 1,221.79 | 76,458 |
| 11 | claude-opus-5.5-medium anthropic | 1,212.75 | 1,205.66 – 1,219.84 | 10,842 |
| 13 | gemini-3.1-pro-grounding google | 1,208.81 | 1,204.13 – 1,213.48 | 151,436 |
| 13 | gpt-5.2-search openai | 1,207.24 | 1,201.7 – 1,212.78 | 55,634 |
| 13 | gemini-3-pro-grounding google | 1,206.47 | 1,201 – 1,211.93 | 38,857 |
| 13 | grok-4.20-multi-agent-beta-0309 xai | 1,204.8 | 1,199.36 – 1,210.24 | 126,238 |
| 14 | claude-opus-4-8 anthropic | 1,204.11 | 1,198.49 – 1,209.73 | 106,304 |
| 15 | gpt-5.1-search openai | 1,199.7 | 1,194.51 – 1,204.89 | 63,042 |
| 15 | gpt-5.4-search openai | 1,199.08 | 1,193.6 – 1,204.57 | 126,730 |
| 18 | gemini-3-flash-grounding google | 1,195.69 | 1,191.39 – 1,200 | 196,399 |
| 20 | claude-sonnet-5-search anthropic | 1,190.94 | 1,184.78 – 1,197.1 | 72,978 |
| 20 | grok-4.20-beta1 xai | 1,190.48 | 1,184.5 – 1,196.45 | 57,049 |
| 23 | claude-opus-4-5-search anthropic | 1,179.58 | 1,173.99 – 1,185.18 | 65,047 |
| 25 | gpt-6-sol-max openai | 1,174.91 | 1,167.84 – 1,181.99 | 11,313 |
| 25 | gpt-5.2-search-non-reasoning openai | 1,171.46 | 1,165.95 – 1,176.98 | 79,796 |
| 25 | grok-4-1-fast-search xai | 1,170.92 | 1,165.96 – 1,175.87 | 85,919 |
| 25 | grok-4-fast-search xai | 1,170.1 | 1,165.47 – 1,174.72 | 43,083 |
| 26 | grok-4.3 xai | 1,165.81 | 1,161.07 – 1,170.54 | 128,393 |
| 30 | claude-sonnet-4-5-search anthropic | 1,160.27 | 1,155.15 – 1,165.39 | 144,153 |
| 27 | gpt-6-luna-max openai | 1,159.56 | 1,152.33 – 1,166.78 | 10,793 |
| 32 | claude-opus-4-1-search anthropic | 1,148.45 | 1,143.58 – 1,153.31 | 79,806 |
| 33 | o3-search openai | 1,144.85 | 1,139.25 – 1,150.44 | 20,770 |
| 33 | gemini-2.5-pro-grounding google | 1,142.8 | 1,138.12 – 1,147.47 | 86,689 |
| 33 | grok-4-search xai | 1,141.86 | 1,135.77 – 1,147.95 | 19,195 |
| 33 | ppl-sonar-reasoning-pro-high perplexity | 1,139.01 | 1,133.19 – 1,144.82 | 29,439 |
| 34 | gpt-5-search openai | 1,133.49 | 1,127.51 – 1,139.47 | 20,865 |
| 36 | ppl-sonar-pro-high perplexity | 1,130.28 | 1,124.47 – 1,136.08 | 28,899 |
| 38 | claude-opus-4-search anthropic | 1,127.43 | 1,122.02 – 1,132.84 | 31,506 |
| 41 | diffbot-small-xl diffbot | 1,022.67 | 1,014.16 – 1,031.17 | 6,368 |
| 41 | api-gpt-4o-search openai | 1,006.58 | 995.37 – 1,017.79 | 3,399 |

## 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 →](/data/rankings/arena-search.json)

 Source files and licences - [metadata · a7a159f557a1](/data/rankings/evidence/a7a159f557a1e594a5d41218fe8d53c63c63daa39b655e51d6fc5b482a17d059.json) · [upstream source ↗](https://huggingface.co/api/datasets/lmarena-ai/leaderboard-dataset)
- [licence · 88a46d472f35](/data/rankings/evidence/88a46d472f35274fb6b7a852c3d16c8ee8007d51b37f290161537bec26895ee4.txt) · [upstream source ↗](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/raw/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/README.md)
- [rows · f9e7c88f4906](/data/rankings/evidence/f9e7c88f49068ca10834991ba1017e9f92d52399541deeb7d79f87acdedfa5d8.parquet) · [upstream source ↗](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/search/latest-00000-of-00001.parquet)

[Explore other model types →](/rankings/)[Read the benchmark guide →](/benchmarks/)

## Continue your investigation

 - [Understand the measurements](/benchmarks/)
- [Compare task performance](/best/)
- [Compare embedding models](/embeddings/)
- [Inspect ranking rules](/methodology/)