Search Arena

View rankings across LLMs with web search for real-time information, external knowledge, and grounded citations
Learn more about Search Arena at our blog

Last Updated

Jan 29, 2026

Total Votes

183,043

Total Models

15

/

/

Style Control

	Rank Spread
1	1◄─►2	gemini-3-pro-grounding	1219	±6	18,839	Google	Proprietary
2	1◄─►3	gpt-5.2-search	1218	±7	12,157	OpenAI	Proprietary
3	2◄─►3	gpt-5.1-search	1207	±6	14,152	OpenAI	Proprietary
4	4◄─►4	grok-4-1-fast-search	1185	±6	14,111	xAI	Proprietary
5	5◄─►5	grok-4-fast-search	1170	±5	31,388	xAI	Proprietary
6	6◄─►10	o3-search	1144	±5	21,056	OpenAI	Proprietary
7	6◄─►10	gemini-2.5-pro-grounding	1143	±4	36,828	Google	Proprietary
8	6◄─►12	ppl-sonar-reasoning-pro-high	1143	±5	29,825	Perplexity	Proprietary
9	6◄─►12	grok-4-search	1142	±5	19,628	xAI	Proprietary
10	6◄─►13	claude-opus-4-1-search	1139	±4	36,199	Anthropic	Proprietary
11	8◄─►13	gpt-5-search	1133	±5	21,212	OpenAI	Proprietary
12	8◄─►13	ppl-sonar-pro-high	1133	±5	29,379	Perplexity	Proprietary
13	10◄─►13	claude-opus-4-search	1132	±5	32,002	Anthropic	Proprietary
14	14◄─►15	diffbot-small-xl	1024	±8	6,473	Diffbot	Apache 2.0
15	14◄─►15	api-gpt-4o-search	1008	±11	3,399	OpenAI	Proprietary

Default Leaderboard Plots

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)