Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Document Understanding on MMLongBenchDoc-C
Loading...
58.2
Accuracy
Synthetic Reasoning
40.728
45.264
49.8
54.336
Mar 31, 2026
Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Accuracy
Synthetic Reasoning
Model family=Qwen3 VL,...
2026.03
58.2
Plain Distillation
Model family=Qwen3 VL,...
2026.03
57.3
LongPO
Model family=Qwen3 VL,...
2026.03
56.4
Qwen3 VL 235B A22B Instruct
Model family=Qwen3 VL,...
2026.03
56.2
No-think
Model family=Qwen3 VL,...
2026.03
54.5
Qwen3 VL 32B Instruct
Model family=Qwen3 VL,...
2026.03
53.8
Synthetic Reasoning
Model family=Mistral,...
2026.03
49.3
Plain Distillation
Model family=Mistral,...
2026.03
47.4
Qwen Thinking Traces
Model family=Mistral,...
2026.03
45.5
No-think
Model family=Mistral,...
2026.03
44.3
Mistral 3.1 Small 24B
Model family=Mistral,...
2026.03
41.4
Feedback
Search any
task
Search any
task