Skip to content

Models Benchmarks Providers

Search models and benchmarks /

MMLongBench-Doc

multimodal

Categories: long context, multimodal, vision
Modality: image
Language: en
Multilingual: No
Max score: 100
Scoring: %, higher is better
Verified by llm-stats: No

MMLongBench-Doc evaluates long document understanding capabilities in vision-language models.

Leaderboard

Showing 5 of 5 results

Qwen3.6 Plus

62.0%

i
Qwen3.5-27B

60.2%

i
Qwen3.5-35B-A3B

59.5%

i
Qwen3.5-122B-A10B

59.0%

i
Qwen3 VL 235B A22B Thinking

56.2%

i

Wikibench About Theme Content licensed CC BY-SA 4.0.