AI Search Leaderboard: Top Models for Research

Search Arena

View overall rankings across LLMs with integrated web search.

Oct 13, 2026

1,437,508 votes

42 models

	Rank Spread
1	13	gpt-5.6-sol-xhigh OpenAI · Proprietary	1261±6	60,437	$4 / $20	1.1M
2	16	qwen3.8-max Alibaba · Proprietary	1261±13	1,870	$1.69 / $5.07	1M
3	16	claude-opus-4-6-search Anthropic · Proprietary	1251±5	173,191	$5 / $25	1M
4	27	gpt-5.5-search OpenAI · Proprietary	1247±5	125,957	$5 / $30	1.1M
5	28	claude-fable-5.1-high Anthropic · Proprietary	1246±7	12,782	$5 / $25	1M
6	211	claude-opus-5-high Anthropic · Proprietary	1242±7	13,285	$5 / $25	1M
7	511	gpt-6-astra-max OpenAI · Proprietary	1234±8	18,483	$10 / $50	1.1M
8	412	gpt-6.1-sol-max OpenAI · Proprietary	1233±9	5,555	$2 / $10	1.1M
9	611	claude-opus-4-7 Anthropic · Proprietary	1230±5	127,506	$5 / $25	1M
10	612	claude-fable-5-high Anthropic · Proprietary	1229±7	73,596	$10 / $50	1M
11	614	ernie-5.1 Baidu · Proprietary	1227±9	4,024	$0.56 / $2.54	119K
12	914	claude-sonnet-4-6-search Anthropic · Proprietary	1221±4	173,986	$1.50 / $7.50	1M
13	1118	grok-4.5 SpaceXAI · Proprietary	1216±6	76,458	$2 / $6	500K
14	1119	claude-opus-5.5-medium Anthropic · Proprietary	1213±7	10,842	$4 / $20	1M
15	1321	gemini-3.1-pro-grounding Google · Proprietary	1209±5	151,436	N/A	N/A
16	1321	gpt-5.2-search OpenAI · Proprietary	1207±6	55,634	$0.88 / $7	400K
17	1321	gemini-3-pro-grounding Google · Proprietary	1206±5	38,857	$2 / $12	N/A
18	1322	grok-4.20-multi-agent-beta-0309 SpaceXAI · Proprietary	1205±5	126,238	$1.25 / $2.50	1M
19	1422	claude-opus-4-8 Anthropic · Proprietary	1204±6	106,304	$5 / $25	1M
20	1524	gpt-5.1-search OpenAI · Proprietary	1200±5	63,042	$0.63 / $5	400K
21	1524	gpt-5.4-search OpenAI · Proprietary	1199±5	126,730	$2.50 / $15	1.1M
22	1824	gemini-3-flash-grounding Google · Proprietary	1196±4	196,399	N/A	N/A
23	2025	claude-sonnet-5-search Anthropic · Proprietary	1191±6	72,978	$2 / $10	1M
24	2025	grok-4.20-beta1 SpaceXAI · Proprietary	1190±6	57,049	N/A	N/A
25	2329	claude-opus-4-5-search Anthropic · Proprietary	1180±6	65,047	$5 / $25	200K
26	2530	gpt-6-sol-max OpenAI · Proprietary	1175±7	11,313	$1 / $5	1.1M
27	2531	gpt-5.2-search-non-reasoning OpenAI · Proprietary	1171±6	79,796	$0.88 / $7	400K
28	2531	grok-4-1-fast-search SpaceXAI · Proprietary	1171±5	85,919	$1.25 / $2.50	2M
29	2531	grok-4-fast-search SpaceXAI · Proprietary	1170±5	43,083	$0.20 / $0.50	2M
30	2632	grok-4.3 SpaceXAI · Proprietary	1166±5	128,393	$1.25 / $2.50	1M
31	3032	claude-sonnet-4-5-search Anthropic · Proprietary	1160±5	144,153	$3 / $15	1M
32	2733	gpt-6-luna-max OpenAI · Proprietary	1160±7	10,793	$0.05 / $0.25	1.1M
33	3237	claude-opus-4-1-search Anthropic · Proprietary	1148±5	79,806	$15 / $75	200K
34	3338	o3-search OpenAI · Proprietary	1145±6	20,770	$1 / $4	200K
35	3338	gemini-2.5-pro-grounding Google · Proprietary	1143±5	86,689	$0.63 / $5	1M
36	3339	grok-4-search SpaceXAI · Proprietary	1142±6	19,195	$3 / $15	N/A
37	3339	ppl-sonar-reasoning-pro-high Perplexity AI · Proprietary	1139±6	29,439	$1 / $1	127.1K
38	3440	gpt-5-search OpenAI · Proprietary	1133±6	20,865	$0.63 / $5	400K
39	3640	ppl-sonar-pro-high Perplexity AI · Proprietary	1130±6	28,899	$1 / $1	127.1K
40	3840	claude-opus-4-search Anthropic · Proprietary	1127±5	31,506	$15 / $75	200K
41	4142	diffbot-small-xl Diffbot · Apache 2.0	1023±9	6,368	N/A	N/A
42	4142	api-gpt-4o-search OpenAI · Proprietary	1007±11	3,399	$30 / $60	8.2K

Search Arena

View overall rankings across LLMs with integrated web search.

Default Leaderboard Plots

Fraction of Model A Wins in A vs. B Battles (Ties Excluded)

Average Win Rate Against Each Opponent (Ties Excluded)

Battle Count for Each Pair of Models (Ties Excluded)

Confidence Intervals on Model Strength (via Bootstrapping)