Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on LongBench Code Repo QA Long v2
Loading...
72.41
Accuracy
BabelTele
43.7164
51.1657
58.615
66.0643
Jun 18, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
BabelTele
Model=GLM-5.1
2026.06
72.41
Original
Model=GLM-5.1
2026.06
62.07
BabelTele
Model=Qwen3.6 Max
2026.06
62.07
Original
Model=Qwen3.6 Max
2026.06
55.17
BabelTele
Model=Kimi2.5
2026.06
48.28
Original
Model=Kimi2.5
2026.06
44.82
Feedback
Search any
task
Search any
task