Ornith 1.0 397B vs Ornith 1.0 31B
Too close to call on our weighted score (Ornith 1.0 397B 51, Ornith 1.0 31B 51). The right pick depends on what you value most.
DeepReinforce
Ornith 1.0 397B
51/100- ECI—
- Price—
- Context262K
DeepReinforce
Ornith 1.0 31B
51/100- ECI—
- Price—
- Context262K
Add a model
Make it a three-way comparison.
Too close to call
It is close. Our weighted score puts them within a point (Ornith 1.0 397B 51/100, Ornith 1.0 31B 51/100), so choose by what matters most for your work: . The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Longest contextAbout the sameOrnith 1.0 397B 262,144 · Ornith 1.0 31B 262,144 tokens
- Widest inputsSame inputsOrnith 1.0 397B: Text, Images · Ornith 1.0 31B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Ornith 1.0 397B | Ornith 1.0 31B |
|---|---|---|---|
| Inputs & features | 60% | 60 | 60 |
| Context window | 40% | 37 | 37 |
| Overall | 100% | 51/100 | 51/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Ornith 1.0 397BDeepReinforce | Ornith 1.0 31BDeepReinforce |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | — | — |
| Output | — | — |
| Cached input | — | — |
| Blended (3:1) | — | — |
| Long-context rate | — | — |
| Price source | — | — |
| Limits | ||
| Context window | 262,144 tokens | 262,144 tokens |
| Max output | — | — |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | Yes | Yes |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | OpenMIT | OpenMIT |
| API model ID | — | — |
| API providers | — | — |
| Released | Jun 25, 2026 | Jun 25, 2026 |
| Knowledge cutoff | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Ornith 1.0 397B—
- Ornith 1.0 31B—
Which should you choose?
Which is better: Ornith 1.0 397B or Ornith 1.0 31B?
It is close. Our weighted score puts them within a point (Ornith 1.0 397B 51/100, Ornith 1.0 31B 51/100), so choose by what matters most for your work: . The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Ornith 1.0 397B or Ornith 1.0 31B?
None of these models has a published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Ornith 1.0 397B has not been scored yet and Ornith 1.0 31B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Ornith 1.0 397B and Ornith 1.0 31B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.
Which has the bigger context window?
Ornith 1.0 397B and Ornith 1.0 31B share the same 262,144-token context window.
Which can read images, PDFs, audio or video?
Ornith 1.0 397B accepts text and images; Ornith 1.0 31B accepts text and images. They handle the same number of input types.
Are any of these open source?
Yes, both publish their weights (MIT), so you can self-host them.
Which is newer?
Ornith 1.0 397B is the newest, released Jun 25, 2026. Ornith 1.0 31B came out Jun 25, 2026.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
