Document High

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

Jul 21, 2026

317,011 votes

32 models

Rank by

	Rank Spread
1	15	claude-opus-4-6 Anthropic · Proprietary	1510±6	37,118	$5 / $25	1M
2	15	claude-opus-4-6-thinking Anthropic · Proprietary	1509±7	24,739	$5 / $25	1M
3	15	claude-fable-5 Anthropic · Proprietary	1505±9	5,565	$10 / $50	1M
4	16	claude-opus-4-7 Anthropic · Proprietary	1501±7	18,738	$5 / $25	1M
5	16	claude-opus-4-7-thinking Anthropic · Proprietary	1499±7	18,522	$5 / $25	1M
6	410	gpt-5.5-high OpenAI · Proprietary	1487±7	16,584	$5 / $30	1.1M
7	610	gpt-5.5 OpenAI · Proprietary	1483±7	17,020	$5 / $30	1.1M
8	610	claude-sonnet-4-6 Anthropic · Proprietary	1483±6	54,339	$3 / $15	1M
9	614	claude-opus-4-8-thinking Anthropic · Proprietary	1474±8	8,117	$5 / $25	1M
10	615	claude-sonnet-5-high Anthropic · Proprietary	1471±11	3,290	$2 / $10	1M
11	914	gpt-5.4 OpenAI · Proprietary	1470±6	29,553	$2.50 / $15	1.1M
12	916	claude-opus-4-8 Anthropic · Proprietary	1467±8	7,874	$5 / $25	1M
13	918	claude-opus-4-5-20251101 Anthropic · Proprietary	1461±10	7,987	$5 / $25	200K
14	919	gemini-3.5-flash-medium Google · Proprietary	1459±11	3,323	$1.50 / $9	1M
15	1219	kimi-k2.6 Moonshot · Modified MIT	1451±8	11,235	$0.95 / $4	262.1K
16	1321	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1445±7	28,479	$3 / $15	200K
17	1126	muse-spark Meta · Proprietary	1444±18	1,085	N/A	N/A
18	1421	gemini-3.1-pro-preview Google · Proprietary	1443±6	44,824	$2 / $12	1M
19	1322	qwen3.7-plus Alibaba · Proprietary	1442±11	2,959	$0.32 / $1.28	1M
20	1625	minimax-m3 MiniMax · MiniMax Community License	1435±8	6,316	$0.60 / $2.40	N/A
21	1626	gemini-3-pro Google · Proprietary	1433±9	10,749	$2 / $12	1M
22	1826	kimi-k2.5-thinking Moonshot · Modified MIT	1430±7	19,702	$0.60 / $3	N/A
23	1929	gemma-4-31b Google · Apache 2.0	1423±8	10,437	N/A	N/A
24	1928	claude-haiku-4-5-20251001 Anthropic · Proprietary	1422±6	30,727	$1 / $5	200K
25	1928	gemini-2.5-pro Google · Proprietary	1421±6	25,023	$1.25 / $10	1M
26	2031	glm-5v-turbo Z.ai · Proprietary	1417±10	4,657	$1.20 / $4	202.8K
27	2332	gemini-3-flash Google · Proprietary	1413±9	7,176	$0.50 / $3	1M
28	2332	grok-4.20-beta-0309-reasoning SpaceXAI · Proprietary	1412±7	18,470	$2 / $6	2M
29	2532	gpt-5.2-high OpenAI · Proprietary	1405±10	7,088	$1.75 / $14	400K
30	2632	gpt-5.5-instant OpenAI · Proprietary	1402±8	8,503	$5 / $30	1.1M
31	2632	gpt-5.1 OpenAI · Proprietary	1401±9	8,241	$1.25 / $10	400K
32	2732	gpt-5.2 OpenAI · Proprietary	1401±6	28,193	$1.75 / $14	400K

Document High

Remove Style Control 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)

Document High

Remove Style Control 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)