Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context document understanding on MMLongBench-Doc (32K context slice)
Loading...
45
MMLongBench-Doc (32K) Score
Qwen3.5-9B
33.56
36.53
39.5
42.47
Jun 5, 2026
MMLongBench-Doc (32K) Score
Performance Gap (32K)
Updated 1mo ago
Evaluation Results
Method
Method
Links
MMLongBench-Doc (32K) Score
Performance Gap (32K)
Qwen3.5-9B
Indexer Type=Dense
2026.06
45
-
Qwen3.5-9B
Indexer Type=Distilled
2026.06
45
0
Qwen3.5-0.8B
Indexer Type=Distilled
2026.06
35
1
Qwen3.5-0.8B
Indexer Type=Dense
2026.06
34
-
Feedback
Search any
task
Search any
task