Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Question Answering on LongBench I. Single-Document QA v2
Loading...
48
Accuracy
MPLM
35.52
38.76
42
45.24
Jul 1, 2026
Accuracy
Latency (s)
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
Latency (s)
MPLM
Backbone=Qwen3.6-35B-A3B
2026.07
48
107.9
RLM
Backbone=Qwen3.6-35B-A3B
2026.07
47.4
233
MPLM
Backbone=Qwen3-30B-A3B
2026.07
38.1
58.2
RLM
Backbone=Qwen3-30B-A3B
2026.07
36
117.3
Feedback
Search any
task
Search any
task
