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 12, 2026

Total Votes

148,614

Total Models

15

/

/

Style Control

	Rank Spread
1	1◄─►3	gemini-3-pro-grounding	1213	±7	11,511	Google	Proprietary
2	1◄─►3	gpt-5.2-search	1210	±8	7,117	OpenAI	Proprietary
3	1◄─►3	gpt-5.1-search	1199	±7	8,877	OpenAI	Proprietary
4	4◄─►4	grok-4-1-fast-search	1178	±7	7,573	xAI	Proprietary
5	5◄─►5	grok-4-fast-search	1164	±5	26,302	xAI	Proprietary
6	6◄─►9	gemini-2.5-pro-grounding	1143	±5	31,350	Google	Proprietary
7	6◄─►9	o3-search	1138	±5	21,174	OpenAI	Proprietary
8	6◄─►11	ppl-sonar-reasoning-pro-high	1137	±5	29,952	Perplexity	Proprietary
9	6◄─►12	grok-4-search	1137	±5	19,725	xAI	Proprietary
10	8◄─►13	claude-opus-4-1-search	1128	±5	30,825	Anthropic	Proprietary
11	8◄─►13	gpt-5-search	1128	±5	21,326	OpenAI	Proprietary
12	9◄─►13	ppl-sonar-pro-high	1127	±5	29,534	Perplexity	Proprietary
13	10◄─►13	claude-opus-4-search	1125	±5	30,901	Anthropic	Proprietary
14	14◄─►15	diffbot-small-xl	1019	±8	6,511	Diffbot	Apache 2.0
15	14◄─►15	api-gpt-4o-search	1004	±10	3,426	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)