---
title: "Search leaderboard"
description: "Rankings of models with integrated web search."
canonical: https://pirouter.ai/rankings/search
last-updated: 2026-10-15
---

# Search leaderboard

> Rankings of models with integrated web search.

- Updated: 2026-08-24
- 2,153,374 votes · 34 models
- Score · higher is better

## Full ranking

| Rank | Rank spread | Model | Vendor | Score | Votes |
|---|---|---|---|---|---|
| 1 | 1–1 | [GPT-5.6 Sol \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-sol) | OpenAI | 1256 ±8 | 29663 |
| 2 | 2–4 | Claude Fable 5 | Anthropic | 1229 ±8 | 41795 |
| 3 | 2–4 | GPT-5.5 Search | OpenAI | 1224 ±6 | 89873 |
| 4 | 2–4 | Claude Opus 4.6 Search | Anthropic | 1223 ±5 | 134699 |
| 5 | 5–9 | Claude Opus 4.7 | Anthropic | 1212 ±6 | 91394 |
| 6 | 5–13 | Gemini 3.1 Pro Grounding | Google | 1208 ±5 | 113282 |
| 7 | 5–15 | Grok 4.20 Multi Agent Beta 0309 | xAI | 1205 ±5 | 109553 |
| 8 | 5–19 | Grok 4.5 | xAI | 1202 ±7 | 31505 |
| 9 | 5–19 | Gemini 3 Pro Grounding | Google | 1201 ±6 | 37024 |
| 10 | 6–19 | Claude Sonnet 4.6 Search | Anthropic | 1201 ±5 | 134905 |
| 11 | 6–20 | Grok 4.20 Beta1 | xAI | 1197 ±6 | 53921 |
| 12 | 6–21 | Claude Sonnet 5 Search | Anthropic | 1196 ±7 | 40230 |
| 13 | 7–22 | Claude Opus 4.8 | Anthropic | 1195 ±6 | 70998 |
| 14 | 7–21 | GPT-5.4 Search | OpenAI | 1195 ±6 | 110116 |
| 15 | 8–21 | Grok 4.1 Fast Search | xAI | 1194 ±5 | 81507 |
| 16 | 6–22 | Ernie 5.1 | Baidu | 1193 ±10 | 3788 |
| 17 | 8–22 | Grok 4.3 | xAI | 1193 ±5 | 91483 |
| 18 | 8–22 | O3 Search | OpenAI | 1192 ±7 | 20644 |
| 19 | 8–22 | Gemini 3 Flash Grounding | Google | 1191 ±5 | 149334 |
| 20 | 11–22 | Claude Opus 4.5 Search | Anthropic | 1187 ±6 | 61573 |
| 21 | 15–23 | GPT-5.1 Search | OpenAI | 1183 ±5 | 59909 |
| 22 | 12–23 | GPT-5 Search | OpenAI | 1183 ±7 | 20781 |
| 23 | 21–24 | Claude Sonnet 4.5 Search | Anthropic | 1175 ±5 | 127378 |
| 24 | 23–26 | Claude Opus 4.1 Search | Anthropic | 1167 ±5 | 76933 |
| 25 | 24–27 | GPT-5.2 Search | OpenAI | 1162 ±6 | 52712 |
| 26 | 24–27 | Grok 4 Fast Search | xAI | 1160 ±5 | 41794 |
| 27 | 25–29 | Claude Opus 4 Search | Anthropic | 1151 ±6 | 31037 |
| 28 | 27–31 | Ppl Sonar Pro (high) | Perplexity | 1143 ±6 | 28519 |
| 29 | 27–31 | Gemini 2.5 Pro Grounding | Google | 1142 ±5 | 83404 |
| 30 | 28–31 | Ppl Sonar Reasoning Pro (high) | Perplexity | 1138 ±6 | 29055 |
| 31 | 28–31 | GPT-5.2 Search Non Reasoning | OpenAI | 1137 ±6 | 75658 |
| 32 | 32–32 | Grok 4 Search | xAI | 1122 ±6 | 19108 |
| 33 | 33–34 | Api GPT 4o Search | OpenAI | 1081 ±11 | 3411 |
| 34 | 33–34 | Diffbot Small Xl | Diffbot | 1062 ±9 | 6388 |

## FAQ

### What is the best AI model for search?

As of 2026-08-24, OpenAI GPT-5.6 Sol (xhigh) is #1 on the search board with a score of 1256, rank spread 1–1.

### What is the best open-weights model for search?

Diffbot Small Xl (Diffbot), #34 on this board.

### What does this board rank?

Rankings of models with integrated web search.

### How often is it updated?

Whenever new models ship or the rankings change; this board was last updated on 2026-08-24.

Data: [LMArena leaderboard dataset](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset), used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); filtered and reasoning tiers merged, scores unchanged.
View the original board: https://arena.ai/leaderboard/search