Search Arena

View overall rankings across LLMs with integrated web search.

May 12, 2026

544,849 votes

29 models

Rank by

	Rank Spread
1	13	claude-opus-4-6-search Anthropic · Proprietary	1251±6	48,724	$5 / $25	1M
2	14	gpt-5.5-search OpenAI · Proprietary	1239±8	9,492	$5 / $30	1.1M
3	14	claude-opus-4-7 Anthropic · Proprietary	1237±8	9,696	$5 / $25	1M
4	29	ernie-5.1 Baidu · Proprietary	1226±12	2,293	N/A	N/A
5	49	claude-sonnet-4-6-search Anthropic · Proprietary	1219±6	48,055	$3 / $15	1M
6	410	gemini-3.1-pro-grounding Google · Proprietary	1216±7	28,011	N/A	N/A
7	412	gpt-5.2-search OpenAI · Proprietary	1210±6	47,097	$1.75 / $14	400K
8	412	grok-4.20-multi-agent-beta-0309 xAI · Proprietary	1209±7	27,452	$2 / $6	2M
9	412	gemini-3-pro-grounding Google · Proprietary	1208±5	37,289	$2 / $12	N/A
10	612	gemini-3-flash-grounding Google · Proprietary	1206±6	62,919	N/A	N/A
11	714	gpt-5.1-search OpenAI · Proprietary	1199±6	53,667	$1.25 / $10	400K
12	714	gpt-5.4-search OpenAI · Proprietary	1199±7	27,862	$2.50 / $15	1.1M
13	1115	grok-4.20-beta1 xAI · Proprietary	1193±6	48,961	N/A	N/A
14	1116	grok-4.3 xAI · Proprietary	1189±8	6,865	$1.25 / $2.50	1M
15	1318	claude-opus-4-5-search Anthropic · Proprietary	1182±6	53,423	$5 / $25	200K
16	1418	gpt-5.2-search-non-reasoning OpenAI · Proprietary	1177±6	65,549	$1.75 / $14	400K
17	1518	grok-4-1-fast-search xAI · Proprietary	1175±5	71,617	$0.20 / $0.50	2M
18	1518	grok-4-fast-search xAI · Proprietary	1172±4	42,951	$0.20 / $0.50	2M
19	1923	claude-sonnet-4-5-search Anthropic · Proprietary	1152±6	45,686	$3 / $15	1M
20	1924	claude-opus-4-1-search Anthropic · Proprietary	1148±5	71,286	$15 / $75	200K
21	1925	o3-search OpenAI · Proprietary	1144±5	20,700	$2 / $8	200K
22	1925	gemini-2.5-pro-grounding Google · Proprietary	1143±5	76,776	$1.25 / $10	1M
23	1925	grok-4-search xAI · Proprietary	1143±6	19,303	$3 / $15	256K
24	2026	ppl-sonar-reasoning-pro-high Perplexity AI · Proprietary	1139±6	29,136	$1 / $1	127.1K
25	2127	gpt-5-search OpenAI · Proprietary	1134±6	20,839	$1.25 / $10	400K
26	2427	ppl-sonar-pro-high Perplexity AI · Proprietary	1130±6	28,623	$1 / $1	127.1K
27	2527	claude-opus-4-search Anthropic · Proprietary	1128±5	31,129	$15 / $75	200K
28	2829	diffbot-small-xl Diffbot · Apache 2.0	1024±8	6,406	N/A	N/A
29	2829	api-gpt-4o-search OpenAI · Proprietary	1006±11	3,413	$30 / $60	8.2K

Search Arena

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)