Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Key-value recall on Memory KV 37 cases (test)
Loading...
37
Accuracy
GPT-5
16.2
21.6
27
32.4
Jun 12, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5
Gen. Traj.=N/A
2026.06
37
Qwen3-4B-Thinking
Gen. Traj.=N/A
2026.06
34
Qwen3-4B-Think + LoRA (1000)
Gen. Traj.=✓
2026.06
34
Qwen3-4B-Think + LoRA (3689)
Gen. Traj.=×
2026.06
31
Qwen3-4B-Think + Full (1000)
Gen. Traj.=✓
2026.06
29
Qwen3-4B-Think + Full (3689)
Gen. Traj.=×
2026.06
28
Qwen3-4B-Instruct
Gen. Traj.=N/A
2026.06
17
Feedback
Search any
task
Search any
task