All benchmarks

OmniDocBench

Progress Over Time

Interactive timeline showing model performance evolution on OmniDocBench

State-of-the-art frontier
Open
Proprietary

OmniDocBench Leaderboard

2 models
ContextCostLicense
1
Moonshot AI
Kimi K3
Moonshot AI
2.8T1.0M$3.00 / $15.00
2
Xiaomi
MiMo-V2.5
Xiaomi
311B1.0M$0.17 / $0.34
Notice missing or incorrect data?
About this benchmark

What is OmniDocBench?

OmniDocBench evaluates multimodal models on document understanding tasks such as OCR, layout parsing, and structured document comprehension.

OmniDocBench is a multimodal benchmark evaluating models on multimodal, document understanding, and vision tasks. LLM Stats tracks 2 models on this benchmark, scored on a 0–1 scale. The current average is 0.9, with the leader at 0.9.

Compare leaders on the best AI for multimodal, best AI for document understanding and best AI for vision leaderboards.

Current leaders

Kimi K3 from Moonshot AI currently leads the OmniDocBench leaderboard with a score of 0.911 across 2 evaluated AI models.

1Kimi K3Moonshot AI91.1%
2MiMo-V2.5Xiaomi87.2%

FAQ

Common questions about the OmniDocBench benchmark and leaderboard.

What is the OmniDocBench benchmark?

OmniDocBench evaluates multimodal models on document understanding tasks such as OCR, layout parsing, and structured document comprehension.

What is the OmniDocBench leaderboard?

The OmniDocBench leaderboard ranks 2 AI models based on their performance on this benchmark. Currently, Kimi K3 by Moonshot AI leads with a score of 0.911. The average score across all models is 0.891.

What is the highest OmniDocBench score?

The highest OmniDocBench score is 0.911, achieved by Kimi K3 from Moonshot AI.

How many models are evaluated on OmniDocBench?

2 models have been evaluated on the OmniDocBench benchmark, with 0 verified results and 2 self-reported results.

What categories does OmniDocBench cover?

OmniDocBench is categorized under multimodal, document understanding, and vision. The benchmark evaluates multimodal models.

What is the best open-source model on OmniDocBench?

Kimi K3 by Moonshot AI is the top-ranked open-source model on OmniDocBench, with a score of 0.911 (rank #1).

Which model offers the best value on OmniDocBench?

Among models scoring within 10% of the leader, MiMo-V2.5 from Xiaomi is the cheapest, at $0.17 per million input tokens with a score of 0.872.

How recent are the OmniDocBench leaderboard results?

The OmniDocBench leaderboard was last updated in July 2026 and currently includes 2 evaluated models.