Search Arena

View overall rankings across LLMs with integrated web search.

Jul 21, 2026

939,947 votes

32 models

Rank by

	Rank Spread
1	11	claude-opus-4-6-search Anthropic · Proprietary	1253±5	112,201	$5 / $25	1M
2	25	gpt-5.5-search OpenAI · Proprietary	1240±5	67,573	$5 / $30	1.1M
3	25	claude-fable-5 Anthropic · Proprietary	1237±8	20,630	$10 / $50	1M
4	25	claude-opus-4-7 Anthropic · Proprietary	1233±5	68,515	$5 / $25	1M
5	27	ernie-5.1 Baidu · Proprietary	1226±10	3,815	N/A	N/A
6	57	claude-sonnet-4-6-search Anthropic · Proprietary	1221±5	111,959	$3 / $15	1M
7	511	gemini-3.1-pro-grounding Google · Proprietary	1212±5	89,973	N/A	N/A
8	713	gemini-3-pro-grounding Google · Proprietary	1207±5	37,255	$2 / $12	N/A
9	714	gpt-5.2-search OpenAI · Proprietary	1206±6	52,718	$1.75 / $14	400K
10	714	grok-4.20-multi-agent-beta-0309 SpaceXAI · Proprietary	1205±5	87,118	$2 / $6	2M
11	714	claude-opus-4-8 Anthropic · Proprietary	1205±6	48,610	$5 / $25	1M
12	816	gpt-5.1-search OpenAI · Proprietary	1199±5	60,019	$1.25 / $10	400K
13	816	gemini-3-flash-grounding Google · Proprietary	1197±5	125,928	N/A	N/A
14	916	gpt-5.4-search OpenAI · Proprietary	1196±5	87,364	$2.50 / $15	1.1M
15	1217	grok-4.20-beta1 SpaceXAI · Proprietary	1189±6	53,877	N/A	N/A
16	1217	claude-sonnet-5-search Anthropic · Proprietary	1188±6	17,604	$2 / $10	1M
17	1520	claude-opus-4-5-search Anthropic · Proprietary	1179±6	61,611	$5 / $25	200K
18	1721	gpt-5.2-search-non-reasoning OpenAI · Proprietary	1173±5	75,752	$1.75 / $14	400K
19	1721	grok-4-1-fast-search SpaceXAI · Proprietary	1171±5	81,860	$0.20 / $0.50	2M
20	1721	grok-4-fast-search SpaceXAI · Proprietary	1170±4	42,981	$0.20 / $0.50	2M
21	1822	grok-4.3 SpaceXAI · Proprietary	1163±5	68,373	$1.25 / $2.50	1M
22	2122	claude-sonnet-4-5-search Anthropic · Proprietary	1158±5	105,762	$3 / $15	1M
23	2327	claude-opus-4-1-search Anthropic · Proprietary	1148±5	77,222	$15 / $75	200K
24	2327	o3-search OpenAI · Proprietary	1143±5	20,785	$2 / $8	200K
25	2328	gemini-2.5-pro-grounding Google · Proprietary	1142±5	83,608	$1.25 / $10	1M
26	2328	grok-4-search SpaceXAI · Proprietary	1141±6	19,379	$3 / $15	N/A
27	2329	ppl-sonar-reasoning-pro-high Perplexity AI · Proprietary	1138±6	29,181	$1 / $1	127.1K
28	2530	gpt-5-search OpenAI · Proprietary	1132±6	20,913	$1.25 / $10	400K
29	2730	ppl-sonar-pro-high Perplexity AI · Proprietary	1129±6	28,703	$1 / $1	127.1K
30	2830	claude-opus-4-search Anthropic · Proprietary	1126±5	31,205	$15 / $75	200K
31	3132	diffbot-small-xl Diffbot · Apache 2.0	1023±8	6,433	N/A	N/A
32	3132	api-gpt-4o-search OpenAI · Proprietary	1006±11	3,437	$30 / $60	8.2K

Search Arena

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)

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