Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
SUCC. on D4 V2
Loading...
4
Critical Depth (d50)
DeepHermes
2.32
13.66
25
36.34
May 26, 2026
Critical Depth (d50)
Updated 7d ago
Evaluation Results
Method
Method
Links
Critical Depth (d50)
DeepHermes
Training Recipe=SFT
2026.05
4
Mistral-Inst
Training Recipe=RLHF
2026.05
4
Qwen3
Training Recipe=RLVR
2026.05
46
Qwen2.5-Inst
Training Recipe=RLHF
2026.05
46
Feedback
Search any
task
Search any
task
