Ornith 1.0 397B
deepreinforce/ornith-1.0-397b
Large coding-reasoning model for agentic software tasks and RL search
Capabilities
ReasoningYes
Tool callingYes
Structured outputNo
TemperatureSupported
AttachmentYes
Open weightsYes
Limits
Context262,144 tokens
Max inputN/A
Max outputN/A
Details
Familyornith
Knowledge cutoffN/A
Release date2026-06-25
Last updated2026-06-25
LicenseMIT
Modalities
Inputtext, image
Outputtext
Benchmarks
SWE-Bench Verified
82.4
percent resolved
SWE-Bench Pro
62.2
percent resolved
SWE-Bench Multilingual
78.9
percent resolved
Terminal-Bench 2.1
77.5
percent
Terminal-Bench 2.1
78.2
percent
NL2Repo
48.2
percent
Claw-eval
77.1
percent
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A