3 results Clear filters
Ranked by raw score for Claw-eval - . Versions are kept separate, and incompatible results are never combined.
Ornith 1.0 397Bby Deepreinforce
2026-06-25
deepreinforce/ornith-1.0-397b

Large coding-reasoning model for agentic software tasks and RL search

T Open weights
Context
262.144K
Input
-
Output
-
Ornith 1.0 35Bby Deepreinforce
2026-06-25
deepreinforce/ornith-1.0-35b

Large coding-reasoning model for agentic software tasks and RL search

T Open weights
Context
262.144K
Input
-
Output
-
Ornith 1.0 9Bby Deepreinforce
2026-06-25
deepreinforce/ornith-1.0-9b

Open coding-reasoning model for repository tasks and self-improving agents

T Open weights
Context
262.144K
Input
-
Output
-