MiMo-V2.6-Pro vs Ornith 1.5 35B A3B vs Qwen 3.8 Max Prime
MiMo-V2.6-Pro comes out ahead, 67 to 59 and 42 on our weighted score, and it is the cheaper option too.
- Our pick
XiaomiMiMo-V2.6-Pro
67/100- ECI—
- Price$0.435 / $0.87
- Context1.05M
DeepReinforce
Ornith 1.5 35B A3B
59/100- ECI—
- Price$0.20 / $1.70
- Context262K
Alibaba (Qwen)Qwen 3.8 Max Prime
42/100- ECI—
- Price$4.00 / $12.00
- Context1M
MiMo-V2.6-Pro is our pick
MiMo-V2.6-Pro is the better all-round choice, scoring 67/100 against Ornith 1.5 35B A3B (59) and Qwen 3.8 Max Prime (42). 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-ProMiMo-V2.6-Pro $0.544 · Ornith 1.5 35B A3B $0.575 · Qwen 3.8 Max Prime $6.00 per 1M tokens (3:1 blend)
- Longest contextMiMo-V2.6-ProMiMo-V2.6-Pro 1,048,576 · Qwen 3.8 Max Prime 1,000,000 · Ornith 1.5 35B A3B 262,144 tokens
- Widest inputsMiMo-V2.6-ProMiMo-V2.6-Pro: Text, Images, Audio, Video · Ornith 1.5 35B A3B: Text, Images · Qwen 3.8 Max Prime: Text, Images, Video
- Self-hostingMiMo-V2.6-Pro and Ornith 1.5 35B A3BPublishes downloadable weights (MIT)
| Measure | Weight | MiMo-V2.6-Pro | Ornith 1.5 35B A3B | Qwen 3.8 Max Prime |
|---|---|---|---|---|
| Price | 50% | 62 | 61 | 13 |
| Inputs & features | 30% | 80 | 70 | 80 |
| Context window | 20% | 61 | 37 | 60 |
| Overall | 100% | 67/100 | 59/100 | 42/100 |
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 | MiMo-V2.6-ProXiaomi | Ornith 1.5 35B A3BDeepReinforce | Qwen 3.8 Max PrimeAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.435 | $0.20 (best) | $4.00 |
| Output | $0.87 (best) | $1.70 | $12.00 |
| Cached input | $0.0036 | — | — |
| Blended (3:1) | $0.544 (best) | $0.575 | $6.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Xiaomi API | Median of 2 providers | Median of 4 providers |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 1,000,000 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 | Yes | No | No |
| Video | Yes | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Open | OpenMIT | Proprietary |
| API model ID | mimo-v2.6-pro | — | — |
| API providers | 16 (best) | 2 | 4 |
| Released | Sep 22, 2026 | Aug 18, 2026 | Sep 23, 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.
- MiMo-V2.6-Pro$6.09
- Ornith 1.5 35B A3B$5.40
- Qwen 3.8 Max Prime$64.00
Which should you choose?
Which is better: MiMo-V2.6-Pro, Ornith 1.5 35B A3B or Qwen 3.8 Max Prime?
MiMo-V2.6-Pro is the better all-round choice, scoring 67/100 against Ornith 1.5 35B A3B (59) and Qwen 3.8 Max Prime (42). 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, MiMo-V2.6-Pro, Ornith 1.5 35B A3B or Qwen 3.8 Max Prime?
MiMo-V2.6-Pro is cheaper at $0.435 input / $0.87 output per million tokens (official Xiaomi API price). Ornith 1.5 35B A3B costs $0.20 input / $1.70 output per million tokens (median across 2 API providers); Qwen 3.8 Max Prime costs $4.00 input / $12.00 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $0.544 per million tokens for MiMo-V2.6-Pro versus $0.575 for Ornith 1.5 35B A3B (1.1× as much) and $6.00 for Qwen 3.8 Max Prime (11× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiMo-V2.6-Pro has not been scored yet, Ornith 1.5 35B A3B has not been scored yet and Qwen 3.8 Max Prime has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiMo-V2.6-Pro, Ornith 1.5 35B A3B and Qwen 3.8 Max Prime 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-Pro has the largest context window at 1,048,576 tokens, against 1,000,000 for Qwen 3.8 Max Prime and 262,144 for Ornith 1.5 35B A3B. Maximum output per response: MiMo-V2.6-Pro up to 131,072, Qwen 3.8 Max Prime up to 131,072 tokens.
Which can read images, PDFs, audio or video?
MiMo-V2.6-Pro accepts text, images, audio and video; Ornith 1.5 35B A3B accepts text and images; Qwen 3.8 Max Prime accepts text, images and video. MiMo-V2.6-Pro handles the widest range of inputs.
Are any of these open source?
MiMo-V2.6-Pro and Ornith 1.5 35B A3B publishes its weights (MIT) and can be self-hosted; Qwen 3.8 Max Prime is proprietary.
Which is newer?
Qwen 3.8 Max Prime is the newest, released Sep 23, 2026. MiMo-V2.6-Pro came out Sep 22, 2026; Ornith 1.5 35B A3B came out Aug 18, 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.
