Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Question Answering on LongBench Long In-context Learning v2
Loading...
49.4
Accuracy
MPLM
25.584
31.767
37.95
44.133
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
49.4
118.1
RLM
Backbone=Qwen3.6-35B-A3B
2026.07
38.3
327.6
MPLM
Backbone=Qwen3-30B-A3B
2026.07
34.9
68.3
RLM
Backbone=Qwen3-30B-A3B
2026.07
26.5
98.5
Feedback
Search any
task
Search any
task
