Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-context Evaluation on LongBench
Loading...
37.97
Average Score
CompilerKV
36.0564
36.5532
37.05
37.5468
Feb 9, 2026
Average Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Score
CompilerKV
Model=LLaMA-3-8B-Instr...
2026.02
37.97
CompilerKV
Model=Mistral-7B-Instr...
2026.02
37.63
CompilerKV
Model=InternLM-2.5-Cha...
2026.02
36.5
CompilerKV
Model=Qwen2-7B-Instruc...
2026.02
36.13
Feedback
Search any
task
Search any
task