Ornith-1.0 brings open-source models for coding agents
Ornith-1.0 is a new open-source family of built for agentic coding work. The released set includes 9B dense models, 35B MoE models, 397B MoE models, and some run-ready compressed versions; the 31B dense model is mentioned in the announcement, but people noticed it was not clearly available in the collection. The team says the 397B model scored 77.5 on and 82.4 on , putting it near or above Claude Opus 4.7 on those tests.
The 35B model is claimed to beat similar-size Qwen and Gemma models across several coding and agent benchmarks. The 9B model is the most interesting for cost: it is small enough for lighter hardware, yet is claimed to match or beat much larger 31B and 35B models on some coding tests. Its training method lets the model improve not only the answer, but also the step-by-step support structure used to solve the task.
Early community reaction is excited, but the real test is whether these numbers hold up in practical agent workloads.
Key points
- Ornith-1.0 is an family aimed at agentic coding.
- The collection includes 9B, 35B, and 397B model sizes, plus compressed run-ready variants.
- The team reports 77.5 on and 82.4 on for the 397B model.
- The 9B model is claimed to perform near much larger models on some coding benchmarks.
- The main value to verify is whether it lowers inference cost for real .