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

Nov 5, 2025

Total Votes

88,195

Total Models

/

Style Control


1	3	grok-4-fast-search	1166	±5	14,957	xAI	Proprietary
2	6	ppl-sonar-pro-high	1149	±4	18,453	Perplexity	Proprietary
2	6	gemini-2.5-pro-grounding	1142	±4	19,350	Google	Proprietary
2	1	o3-search	1142	±4	19,254	OpenAI	Proprietary
2	9	grok-4-search	1141	±4	18,132	xAI	Proprietary
6	1	gpt-5-search	1132	±4	18,997	OpenAI	Proprietary
6	3	claude-opus-4-1-search	1132	±4	19,123	Anthropic	Proprietary
6	3	claude-opus-4-search	1130	±4	19,344	Anthropic	Proprietary
6	8	ppl-sonar-reasoning-pro-high	1127	±4	18,881	Perplexity	Proprietary
10	10	diffbot-small-xl	1023	±7	6,433	Diffbot	Apache 2.0
10	10	api-gpt-4o-search	1011	±10	3,466	OpenAI	Proprietary

Take your chats anywhere

Search Arena

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)

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