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

Oct 9, 2025

Total Votes

67,635

Total Models

/


1	3	grok-4-fast-search	1164	±6	10,309	xAI	Proprietary
2	3	gemini-2.5-pro-grounding	1142	±5	14,863	Google	Proprietary
2	1	o3-search	1142	±5	14,712	OpenAI	Proprietary
2	8	grok-4-search	1140	±5	14,115	xAI	Proprietary
2	6	ppl-sonar-pro-high	1138	±5	13,869	Perplexity	Proprietary
2	1	gpt-5-search	1133	±5	14,547	OpenAI	Proprietary
6	3	claude-opus-4-1-search	1128	±5	14,561	Anthropic	Proprietary
6	3	claude-opus-4-search	1128	±5	14,758	Anthropic	Proprietary
9	8	ppl-sonar-reasoning-pro-high	1115	±5	14,311	Perplexity	Proprietary
10	10	diffbot-small-xl	1022	±8	5,729	Diffbot	Apache 2.0
10	10	api-gpt-4o-search	1006	±10	3,496	OpenAI	Proprietary

Take your chats anywhere

Search Arena

Default Leaderboard Plots

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)

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