Ornith-1.5-397B
Ornith AIOpen weightsReasoningProvisionalReleased Aug 18, 2026
Overall score
62.3
Rank 49 of 222 · 47.9–76.6
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.
- 1Agentic & tool use75.6
- 2Knowledge71.0
- 3Coding66.7
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 | 86.1 | #14 of 68 |
| BrowseComp | 86.6 | #12 of 50 |
| MCP Atlas | 80.0 | #11 of 42 |
| Claw-Eval | 81.4 | #1 of 36 |
| HLE w/ tools | 56.1 | #12 of 27 |
| Toolathlon-Verified | 71.2 | #16 of 22 |
| WideResearch | 80.8 | #5 of 16 |
| Terminal-Bench 3.0 | 13.5 | #11 of 13 |
Coding
| SWE-bench Verified | 86.0 | #7 of 98 |
| SWE-bench Pro | 65.1 | #12 of 69 |
| DeepSWE | 56.0 | #41 of 50 |
| NL2Repo | 59.5 | #4 of 31 |
Knowledge
| GPQA | 92.8 | #9 of 117 |
| HLE | 44.6 | #24 of 69 |
| HLE w/o tools | 44.6 | #12 of 43 |
Multilingual
| SWE Multilingual | 79.6 | #12 of 46 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
Ornith publishes the MIT-licensed Ornith-1.5-397B 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
Similar score
- Claude Opus 4.662.3 · $10.00
- Qwen3.7 Max62.6 · $2.21
- Gemini 3.5 Flash61.9 · $3.38
- Muse Spark Open62.8 · $2.00
- Gemini 3.6 Flash62.8 · $1.50