Arena benchmark
LM Arena Document Leaderboard
LM Arena Document model ratings and results.
Updated Aug 17, 2026. Data as of 2026-08-17
Models33
Categories1
Result typerating
Document Ranking
Models are ordered by their Arena rank.
Sort by
Rank | Model | Organization | Rating / score | Votes | Observations | Result date |
|---|
| Rank01 | ModelAN | Organizationanthropic | Rating / score1520.1 | Votes1,663 | ObservationsN/A | Result date |
| Rank02 | ModelAN | Organizationanthropic | Rating / score1509.9 | Votes37,271 | ObservationsN/A | Result date |
| Rank04 | ModelAN | Organizationanthropic | Rating / score1504.2 | Votes5,792 | ObservationsN/A | Result date |
| Rank05 | ModelAN | Organizationanthropic | Rating / score1498.1 | Votes18,990 | ObservationsN/A | Result date |
| Rank07 | ModelOP | Organizationopenai | Rating / score1484.7 | Votes16,816 | ObservationsN/A | Result date |
| Rank08 | ModelAN | Organizationanthropic | Rating / score1482.8 | Votes54,427 | ObservationsN/A | Result date |
| Rank10 | ModelOP | Organizationopenai | Rating / score1479.2 | Votes1,969 | ObservationsN/A | Result date |
| Rank11 | ModelOP | Organizationopenai | Rating / score1478.7 | Votes1,152 | ObservationsN/A | Result date |
| Rank12 | ModelAN | Organizationanthropic | Rating / score1474.6 | Votes8,388 | ObservationsN/A | Result date |
| Rank13 | ModelME | Organizationmeta | Rating / score1471.7 | Votes2,054 | ObservationsN/A | Result date |
| Rank14 | ModelAN | Organizationanthropic | Rating / score1470.2 | Votes3,601 | ObservationsN/A | Result date |
| Rank15 | ModelOP | Organizationopenai | Rating / score1470.1 | Votes29,809 | ObservationsN/A | Result date |
| Rank17 | ModelGO | Organizationgoogle | Rating / score1464.6 | Votes3,689 | ObservationsN/A | Result date |
| Rank18 | ModelOP | Organizationopenai | Rating / score1462.3 | Votes1,888 | ObservationsN/A | Result date |
| Rank19 | ModelAN | Organizationanthropic | Rating / score1461.7 | Votes7,965 | ObservationsN/A | Result date |
| Rank20 | ModelXA | Organizationxai | Rating / score1453.7 | Votes2,435 | ObservationsN/A | Result date |
| Rank21 | ModelMA | Organizationmoonshot | Rating / score1450.9 | Votes11,181 | ObservationsN/A | Result date |
| Rank22 | ModelAN | Organizationanthropic | Rating / score1446.2 | Votes28,634 | ObservationsN/A | Result date |
| Rank23 | ModelGO | Organizationgoogle | Rating / score1445.3 | Votes45,162 | ObservationsN/A | Result date |
| Rank24 | ModelME | Organizationmeta | Rating / score1443.2 | Votes1,078 | ObservationsN/A | Result date |
| Rank25 | ModelAC | Organizationalibaba | Rating / score1439.6 | Votes3,088 | ObservationsN/A | Result date |
| Rank26 | ModelMI | Organizationminimax | Rating / score1434.8 | Votes6,263 | ObservationsN/A | Result date |
| Rank27 | ModelGO | Organizationgoogle | Rating / score1433.0 | Votes10,739 | ObservationsN/A | Result date |
| Rank28 | ModelMA | Organizationmoonshot | Rating / score1429.5 | Votes19,891 | ObservationsN/A | Result date |
| Rank29 | ModelGO | Organizationgoogle | Rating / score1423.7 | Votes10,577 | ObservationsN/A | Result date |
| Rank30 | ModelAN | Organizationanthropic | Rating / score1423.0 | Votes30,937 | ObservationsN/A | Result date |
| Rank31 | ModelGO | Organizationgoogle | Rating / score1420.9 | Votes24,963 | ObservationsN/A | Result date |
| Rank32 | ModelZA | Organizationzai | Rating / score1417.2 | Votes4,894 | ObservationsN/A | Result date |
| Rank33 | ModelXA | Organizationxai | Rating / score1413.9 | Votes18,666 | ObservationsN/A | Result date |
| Rank34 | ModelGO | Organizationgoogle | Rating / score1413.3 | Votes7,173 | ObservationsN/A | Result date |
| Rank35 | ModelOP | Organizationopenai | Rating / score1405.0 | Votes7,073 | ObservationsN/A | Result date |
| Rank36 | ModelOP | Organizationopenai | Rating / score1401.6 | Votes8,442 | ObservationsN/A | Result date |
| Rank37 | ModelOP | Organizationopenai | Rating / score1400.8 | Votes8,220 | ObservationsN/A | Result date |
Document Rating Distribution
A closer view of the leading model ratings.
The Top AI Models for Document
The first five models in this source ranking, with price and output speed included when a canonical model match is available.
Ranking basisThis document AI model leaderboard uses the source rating and Arena rank. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ANClaude Opus 5Anthropic
- rating
- 1,520
- Price
- $5.0 input / $25 output per 1M tokens
- Speed
- Up to 3.3 tok/s via Anthropic
Strengths
- Ranks #1 on Document
- 1,663 votes support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 02ANClaude Opus 4.6Anthropic
- rating
- 1,510
- Price
- $5.0 input / $25 output per 1M tokens
- Speed
- Up to 17 tok/s via Anthropic
Strengths
- Ranks #2 on Document
- 37,271 votes support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 04ANClaude Fable 5Anthropic
- rating
- 1,504
- Price
- $10 input / $50 output per 1M tokens
- Speed
- Up to 9.1 tok/s via Anthropic
Strengths
- Ranks #4 on Document
- 5,792 votes support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 05ANClaude Opus 4.7Anthropic
- rating
- 1,498
- Price
- $5.0 input / $25 output per 1M tokens
- Speed
- Up to 42 tok/s via Anthropic
Strengths
- Ranks #5 on Document
- 18,990 votes support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 07OPGPT-5.5OpenAI
- rating
- 1,485
- Price
- $5.0 input / $30 output per 1M tokens
Strengths
- Ranks #7 on Document
- 16,816 votes support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
Selection summary
Best AI Models for Document
Claude Opus 5 currently leads Document at 1,520. The best AI model for this use case may change when price, speed and independent benchmark capability are considered.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is the Document Arena?
What Document measures and how to read its results.
Document reports rating values and currently defines 1 evaluation category.
Arena results are preference or task-outcome signals. They are not automatically equivalent to capability benchmark scores.
FAQ
Common questions about Document.
Which model leads Document?
Claude Opus 5 is currently ranked first.
What does Document measure?
This Arena reports rating values across 1 configured evaluation category.
Does this result affect the LLMBoard score?
No. Arena results remain a separate preference or task-outcome signal.
How many models are included?
33 model results are currently shown.