MMLongBench-Doc
Progress Over Time
Interactive timeline showing model performance evolution on MMLongBench-Doc
State-of-the-art frontier
Open
Proprietary
MMLongBench-Doc Leaderboard
7 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  NVIDIA | 120B | 262K | $0.20 / $1.00 | ||
| 2 |  Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 3 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.26 / $2.60 | ||
| 4 | Alibaba Cloud / Qwen Team | 35B | 262K | $0.14 / $1.00 | ||
| 5 | Alibaba Cloud / Qwen Team | 122B | 262K | $0.29 / $2.40 | ||
| 6 | Alibaba Cloud / Qwen Team | 236B | — | — | ||
| 7 |  ByteDance | — | 256K | $0.10 / $0.40 |
Notice missing or incorrect data?
What is MMLongBench-Doc?
MMLongBench-Doc evaluates long document understanding capabilities in vision-language models.
MMLongBench-Doc is a image benchmark evaluating models on long context, multimodal, and vision tasks. LLM Stats tracks 7 models on this benchmark, scored on a 0–100 scale. The current average is 0.6, with the leader at 0.6.
Compare leaders on the best AI for long context, best AI for multimodal and best AI for vision leaderboards.
Current leaders
Nemotron 3.5 Super VL (120B A12B) from NVIDIA currently leads the MMLongBench-Doc leaderboard with a score of 0.628 across 7 evaluated AI models.
FAQ
Common questions about the MMLongBench-Doc benchmark and leaderboard.