Ornith-1.5-35B-A3B
Ornith AIOpen weightsReasoningProvisionalReleased Aug 18, 2026
Overall score
34.0
Rank 165 of 222 · 19.7–48.4
Context window
262K
262,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Coding54.7
- 2Agentic & tool use49.9
- 3Knowledge45.7
Benchmark results (16)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| Terminal-Bench 2.1 | 67.8 | #43 of 68 |
| BrowseComp | 67.6 | #34 of 50 |
| MCP Atlas | 70.2 | #25 of 42 |
| Claw-Eval | 72.5 | #6 of 36 |
| HLE w/ tools | 33.4 | #26 of 27 |
| Toolathlon-Verified | 48.7 | #21 of 22 |
| WideResearch | 67.8 | #14 of 16 |
| Terminal-Bench 3.0 | 5.1 | #12 of 13 |
Coding
| SWE-bench Verified | 79.0 | #21 of 98 |
| SWE-bench Pro | 59.6 | #27 of 69 |
| DeepSWE | 22.0 | #50 of 50 |
| NL2Repo | 46.2 | #17 of 31 |
Knowledge
| GPQA | 89.2 | #30 of 117 |
| HLE | 25.6 | #52 of 69 |
| HLE w/o tools | 25.6 | #36 of 43 |
Multilingual
| SWE Multilingual | 71.4 | #33 of 46 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
Ornith publishes the MIT-licensed Ornith-1.5-35B-A3B checkpoint on Hugging Face for self-hosted use. Ornith does not publish a first-party hosted API token price for this exact model, so BenchLM represents it as self-host/free-per-token before infrastructure costs.
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Same family
- Ornith-1.5-397B62.3
- Ornith-1.5-9B31.7
Similar score
- Mercury 2.534.0 · $0.068
- Grok Code Fast 134.1 · $0.53
- Mercury 233.7 · $0.38
- Mistral Medium 3.5 128B33.6 · $3.00
- Trinity-Large-Thinking34.5 · $0.41