Document Arena

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

Mar 2, 2026

31,666 votes

11 models

	Rank Spread
1	11	claude-opus-4-6 Anthropic · Proprietary	1525±12	3,584
2	23	claude-opus-4-5-20251101 Anthropic · Proprietary	1474±12	5,368
3	25	gemini-3.1-pro-preview Google · Proprietary	1462±16	1,266
4	36	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1450±11	5,530
5	37	gemini-3-pro Google · Proprietary	1444±10	7,569
6	49	gemini-2.5-pro Google · Proprietary	1433±10	5,407
7	511	claude-haiku-4-5-20251001 Anthropic · Proprietary	1426±12	4,779
8	611	gemini-3-flash Google · Proprietary	1422±9	7,127
9	611	gpt-5.1 OpenAI · Proprietary	1413±10	5,670
10	711	gpt-5.2-high OpenAI · Proprietary	1412±10	4,492
11	711	gpt-5.2 OpenAI · Proprietary	1410±10	6,916

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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

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