DeepReinforce
Ornith 1.0 9B
Open coding-reasoning model for repository tasks and self-improving agents
deepreinforce/ornith-1.0-9b
Context
262.1K
Output
—
Released
2026-06-25
Knowledge cutoff
—
Types
InputTextImage
OutputText
Reasoning
Supported
Tool use
Supported
Structured output
—
Attachments
Supported
Open weights
Supported
Provider pricing
No providers currently list this model.
Benchmarks
SWE-Bench Verified
69.4 · percent resolved
SWE-Bench Pro
42.9 · percent resolved
SWE-Bench Multilingual
52 · percent resolved
Terminal-Bench 2.1
43.1 · percent
Terminal-Bench 2.1
40.6 · percent
NL2Repo
27.2 · percent
Claw-eval
63.1 · percent