# Ornith 1.0 35B Usage, Cost & Rank | OpenCode Data

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

- Page: https://opencode.ai/data/deepreinforce/ornith-1-0-35b
- JSON: https://opencode.ai/data/deepreinforce/ornith-1-0-35b.json
- Model ID: deepreinforce/ornith-1.0-35b
- Lab: DeepReinforce

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 262K |
| Max output | - |
| Knowledge cutoff | - |
| Release date | 2026-06-25 |
| Input modalities | text, image |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| SWE-Bench Verified | 75.6 | percent resolved | https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B |
| SWE-Bench Pro | 50.4 | percent resolved | https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B |
| SWE-Bench Multilingual | 69.3 | percent resolved | https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B |
| Terminal-Bench 2.1 | 64.2 | percent | https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B |
| Terminal-Bench 2.1 | 62.8 | percent | https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B |
| NL2Repo | 34.6 | percent | https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B |
| Claw-eval | 69.8 | percent | https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.