Document Arena

View overall rankings across AI models in document analysis and long-content reasoning.

Jun 10, 2026

252,314 votes

29 models

Rank by

	Rank Spread
1	15	claude-opus-4-6 Anthropic · Proprietary	1507±6	32,122	$5 / $25	1M
2	15	claude-opus-4-6-thinking Anthropic · Proprietary	1507±7	20,246	$5 / $25	1M
3	17	claude-opus-4-7-thinking Anthropic · Proprietary	1498±7	13,878	$5 / $25	1M
4	18	claude-opus-4-7 Anthropic · Proprietary	1496±7	14,110	$5 / $25	1M
5	111	claude-fable-5 Anthropic · Proprietary	1495±15	1,461	$10 / $50	1M
6	310	claude-sonnet-4-6 Anthropic · Proprietary	1487±6	49,424	$3 / $15	1M
7	311	gpt-5.5-high OpenAI · Proprietary	1485±7	11,789	$5 / $30	1.1M
8	411	gpt-5.5 OpenAI · Proprietary	1483±7	12,050	$5 / $30	1.1M
9	612	gpt-5.4 OpenAI · Proprietary	1474±7	24,400	$2.50 / $15	1.1M
10	512	claude-opus-4-8-thinking Anthropic · Proprietary	1473±11	3,431	$5 / $25	1M
11	512	claude-opus-4-8 Anthropic · Proprietary	1472±11	3,223	$5 / $25	1M
12	915	claude-opus-4-5-20251101 Anthropic · Proprietary	1461±10	7,987	$5 / $25	200K
13	1217	kimi-k2.6 Moonshot · Modified MIT	1451±8	8,574	$0.95 / $4	262.1K
14	1217	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1449±7	24,162	$3 / $15	200K
15	1223	muse-spark Meta · Proprietary	1442±18	1,081	N/A	N/A
16	1319	gemini-3.1-pro-preview Google · Proprietary	1441±6	38,090	$2 / $12	1M
17	1321	minimax-m3 MiniMax · Proprietary	1438±10	3,636	$0.60 / $2.40	N/A
18	1523	gemini-3-pro Google · Proprietary	1433±9	10,748	$2 / $12	1M
19	1523	kimi-k2.5-thinking Moonshot · Modified MIT	1429±7	16,540	$0.60 / $3	N/A
20	1625	gemma-4-31b Google · Apache 2.0	1424±9	7,970	N/A	N/A
21	1726	gemini-2.5-pro Google · Proprietary	1420±6	24,980	$1.25 / $10	1M
22	1726	claude-haiku-4-5-20251001 Anthropic · Proprietary	1418±6	26,371	$1 / $5	200K
23	1629	glm-5v-turbo Z.ai · Proprietary	1413±15	1,389	$1.20 / $4	202.8K
24	2029	gemini-3-flash Google · Proprietary	1413±9	7,188	$0.50 / $3	1M
25	2029	grok-4.20-beta-0309-reasoning xAI · Proprietary	1410±7	14,105	$2 / $6	2M
26	2129	gpt-5.2-high OpenAI · Proprietary	1405±9	7,096	$1.75 / $14	400K
27	2329	gpt-5.5-instant OpenAI · Proprietary	1402±8	8,539	$5 / $30	1.1M
28	2329	gpt-5.1 OpenAI · Proprietary	1401±9	8,253	$1.25 / $10	400K
29	2329	gpt-5.2 OpenAI · Proprietary	1401±6	28,188	$1.75 / $14	400K

Document Arena

Remove Style Control 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)