Ornith 1.5 35B A3B vs MiMo-V2.6-Flash vs Muse Glimmer 30B
MiMo-V2.6-Flash comes out ahead, 79 to 59 and 57 on our weighted score, and it is the cheaper option too.
DeepReinforce
Ornith 1.5 35B A3B
59/100- ECI—
- Price$0.20 / $1.70
- Context262K
- Our pick
XiaomiMiMo-V2.6-Flash
79/100- ECI—
- Price$0.14 / $0.28
- Context1.05M
MetaMuse Glimmer 30B
57/100- ECI—
- Price$0.30 / $1.20
- Context131K
MiMo-V2.6-Flash is our pick
MiMo-V2.6-Flash is the better all-round choice, scoring 79/100 against Ornith 1.5 35B A3B (59) and Muse Glimmer 30B (57). It leads on price, inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. 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
- Lowest priceMiMo-V2.6-FlashMiMo-V2.6-Flash $0.175 · Muse Glimmer 30B $0.525 · Ornith 1.5 35B A3B $0.575 per 1M tokens (3:1 blend)
- Longest contextMiMo-V2.6-FlashMiMo-V2.6-Flash 1,048,576 · Ornith 1.5 35B A3B 262,144 · Muse Glimmer 30B 131,072 tokens
- Widest inputsMiMo-V2.6-FlashOrnith 1.5 35B A3B: Text, Images · MiMo-V2.6-Flash: Text, Images, Audio, Video · Muse Glimmer 30B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Ornith 1.5 35B A3B | MiMo-V2.6-Flash | Muse Glimmer 30B |
|---|---|---|---|---|
| Price | 50% | 61 | 86 | 63 |
| Inputs & features | 30% | 70 | 80 | 70 |
| Context window | 20% | 37 | 61 | 24 |
| Overall | 100% | 59/100 | 79/100 | 57/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Ornith 1.5 35B A3BDeepReinforce | MiMo-V2.6-FlashXiaomi | Muse Glimmer 30BMeta |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.20 | $0.14 (best) | $0.30 |
| Output | $1.70 | $0.28 (best) | $1.20 |
| Cached input | — | $0.0028 | — |
| Blended (3:1) | $0.575 | $0.175 (best) | $0.525 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Official Xiaomi API | Median of 10 providers |
| Limits | |||
| Context window | 262,144 tokens | 1,048,576 tokens (best) | 131,072 tokens |
| Max output | — | 131,072 tokens | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | OpenMIT | Open | OpenApache 2.0 |
| API model ID | — | mimo-v2.6-flash | — |
| API providers | 2 | 18 (best) | 12 |
| Released | Aug 18, 2026 | Sep 22, 2026 | Aug 10, 2026 |
| Knowledge cutoff | — | — | Jan 4, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Ornith 1.5 35B A3B$5.40
- MiMo-V2.6-Flash$1.96
- Muse Glimmer 30B$5.40
Which should you choose?
Which is better: Ornith 1.5 35B A3B, MiMo-V2.6-Flash or Muse Glimmer 30B?
MiMo-V2.6-Flash is the better all-round choice, scoring 79/100 against Ornith 1.5 35B A3B (59) and Muse Glimmer 30B (57). It leads on price, inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Ornith 1.5 35B A3B, MiMo-V2.6-Flash or Muse Glimmer 30B?
MiMo-V2.6-Flash is cheaper at $0.14 input / $0.28 output per million tokens (official Xiaomi API price). Muse Glimmer 30B costs $0.30 input / $1.20 output per million tokens (median across 10 API providers); Ornith 1.5 35B A3B costs $0.20 input / $1.70 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for MiMo-V2.6-Flash versus $0.525 for Muse Glimmer 30B (3× as much) and $0.575 for Ornith 1.5 35B A3B (3.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Ornith 1.5 35B A3B has not been scored yet, MiMo-V2.6-Flash has not been scored yet and Muse Glimmer 30B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Ornith 1.5 35B A3B, MiMo-V2.6-Flash and Muse Glimmer 30B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
MiMo-V2.6-Flash has the largest context window at 1,048,576 tokens, against 262,144 for Ornith 1.5 35B A3B and 131,072 for Muse Glimmer 30B. Maximum output per response: MiMo-V2.6-Flash up to 131,072, Muse Glimmer 30B up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Ornith 1.5 35B A3B accepts text and images; MiMo-V2.6-Flash accepts text, images, audio and video; Muse Glimmer 30B accepts text and images. MiMo-V2.6-Flash handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (MIT and Apache 2.0), so you can self-host them.
Which is newer?
MiMo-V2.6-Flash is the newest, released Sep 22, 2026. Ornith 1.5 35B A3B came out Aug 18, 2026; Muse Glimmer 30B came out Aug 10, 2026. Knowledge cutoff: Muse Glimmer 30B Jan 4, 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.
