Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-context Document Understanding on MMLB 128K
Loading...
78.6
Accuracy
Qwen3 VL
65.184
68.667
72.15
75.633
Feb 16, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3 VL
Checkpoint=235B A22B
2026.02
78.6
LongPO
Checkpoint=Short Stage
2026.02
75.6
Qwen3 VL Plain Distillation
Checkpoint=Short Stage
2026.02
73.8
Qwen3 VL
Checkpoint=32B
2026.02
70.4
Mistral 3.1 Small
Checkpoint=24B
2026.02
66.4
Mistral Plain Distillation*
2026.02
65.7
Feedback
Search any
task
Search any
task