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

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

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

[All rankings](/rankings/) / Search and documents

# Search · factuality

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

**40 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 · factuality · Arena score

| Significance rank | Model / evaluated variant | Arena score | 95% confidence interval | Votes |
| --- | --- | --- | --- | --- |
| 1 | gpt-5.6-sol-xhigh openai | 1,251.13 | 1,246.28 – 1,255.97 | 60,437 |
| 1 | gpt-5.5-search openai | 1,247.32 | 1,243.44 – 1,251.21 | 125,914 |
| 1 | qwen3.8-max alibaba | 1,240.45 | 1,228.61 – 1,252.29 | 1,870 |
| 2 | gpt-6-astra-max openai | 1,239.92 | 1,233.58 – 1,246.27 | 18,483 |
| 2 | gpt-6.1-sol-max openai | 1,236.13 | 1,228.31 – 1,243.95 | 5,555 |
| 4 | claude-opus-4-6-search anthropic | 1,226.82 | 1,223.6 – 1,230.04 | 173,142 |
| 6 | gpt-5.2-search openai | 1,224.01 | 1,220.12 – 1,227.9 | 55,464 |
| 6 | claude-fable-5.1-high anthropic | 1,221.53 | 1,215.4 – 1,227.67 | 12,782 |
| 6 | grok-4.5 xai | 1,219.92 | 1,215.44 – 1,224.39 | 76,458 |
| 7 | claude-opus-5-high anthropic | 1,216.86 | 1,210.71 – 1,223.02 | 13,285 |
| 7 | ernie-5.1 baidu | 1,213.76 | 1,204.71 – 1,222.81 | 4,024 |
| 8 | gpt-5.4-search openai | 1,212.94 | 1,209.1 – 1,216.79 | 126,672 |
| 8 | claude-fable-5-high anthropic | 1,212.31 | 1,207.32 – 1,217.3 | 73,596 |
| 10 | claude-opus-4-7 anthropic | 1,210.18 | 1,206.44 – 1,213.92 | 127,472 |
| 10 | claude-opus-5.5-medium anthropic | 1,205.19 | 1,198.86 – 1,211.51 | 10,842 |
| 12 | gpt-5.1-search openai | 1,203.48 | 1,199.43 – 1,207.53 | 62,869 |
| 14 | claude-sonnet-4-6-search anthropic | 1,201.77 | 1,198.37 – 1,205.16 | 173,930 |
| 15 | gpt-5.2-search-non-reasoning openai | 1,197.96 | 1,194.71 – 1,201.21 | 79,609 |
| 15 | gpt-6-sol-max openai | 1,197.85 | 1,191.94 – 1,203.77 | 11,313 |
| 15 | grok-4.20-multi-agent-beta-0309 xai | 1,197.77 | 1,193.6 – 1,201.94 | 126,186 |
| 15 | claude-opus-4-8 anthropic | 1,197.29 | 1,192.84 – 1,201.74 | 106,304 |
| 15 | gemini-3.1-pro-grounding google | 1,196.99 | 1,193.3 – 1,200.67 | 151,380 |
| 15 | grok-4.20-beta1 xai | 1,195.77 | 1,191.31 – 1,200.23 | 56,876 |
| 18 | gemini-3-pro-grounding google | 1,193.45 | 1,188.66 – 1,198.24 | 38,729 |
| 24 | gpt-6-luna-max openai | 1,183 | 1,177.08 – 1,188.91 | 10,793 |
| 25 | claude-sonnet-5-search anthropic | 1,181.75 | 1,176.92 – 1,186.59 | 72,978 |
| 25 | claude-opus-4-5-search anthropic | 1,180.91 | 1,176.56 – 1,185.25 | 64,860 |
| 25 | gemini-3-flash-grounding google | 1,179.13 | 1,175.72 – 1,182.54 | 196,216 |
| 25 | grok-4.3 xai | 1,174.99 | 1,171.24 – 1,178.74 | 128,393 |
| 30 | claude-sonnet-4-5-search anthropic | 1,162.49 | 1,158.51 – 1,166.47 | 143,960 |
| 30 | gemini-2.5-pro-grounding google | 1,162.4 | 1,158.92 – 1,165.88 | 69,356 |
| 30 | ppl-sonar-reasoning-pro-high perplexity | 1,155.58 | 1,149.14 – 1,162.01 | 12,927 |
| 32 | claude-opus-4-1-search anthropic | 1,154.09 | 1,150.02 – 1,158.17 | 62,796 |
| 32 | grok-4-1-fast-search xai | 1,152.02 | 1,148.18 – 1,155.86 | 85,736 |
| 32 | grok-4-fast-search xai | 1,146 | 1,141.23 – 1,150.76 | 30,673 |
| 32 | gpt-5-search openai | 1,143.97 | 1,134.48 – 1,153.46 | 4,004 |
| 35 | claude-opus-4-search anthropic | 1,139.6 | 1,133.53 – 1,145.67 | 14,486 |
| 36 | ppl-sonar-pro-high perplexity | 1,132.63 | 1,126.14 – 1,139.12 | 12,844 |
| 35 | grok-4-search xai | 1,131.13 | 1,120.61 – 1,141.66 | 3,189 |
| 36 | o3-search openai | 1,129.23 | 1,119.13 – 1,139.32 | 3,818 |

## 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-factuality.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 · c4588e6f78f5](/data/rankings/evidence/c4588e6f78f5a65444d1fde2bb0733e8ccdabb46db2af7e6345c631eefe90e5a.parquet) · [upstream source ↗](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/search_factuality/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/)