Model Comparator
Compare up to four models using the same criteria.
2 models compared
- MiMo-V2.5
Xiaomi
- G9v3-39A5B
AI9Stars
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | MiMo-V2.5 Xiaomi | G9v3-39A5B AI9Stars | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 21.8 | 21.8 | |
| Coding | Best: 56.8 | 33.1 | |
| Agentic | 15.8 | — | |
| Speed | 36.1 t/s | — | |
| TTFT | 4.63 s | — | |
| Input · $ / 1M tokens | $0.14 | — | |
| Output · $ / 1M tokens | $0.28 | — | |
| Context window | Best: 1M | 131K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0191 | — |
Intelligence
- MiMo-V2.5
- 21.8
- G9v3-39A5B
- 21.8
Coding
- MiMo-V2.5
- Best: 56.8
- G9v3-39A5B
- 33.1
Agentic
- MiMo-V2.5
- 15.8
- G9v3-39A5B
- —
Speed
- MiMo-V2.5
- 36.1 t/s
- G9v3-39A5B
- —
TTFT
- MiMo-V2.5
- 4.63 s
- G9v3-39A5B
- —
Input · $ / 1M tokens
- MiMo-V2.5
- $0.14
- G9v3-39A5B
- —
Output · $ / 1M tokens
- MiMo-V2.5
- $0.28
- G9v3-39A5B
- —
Context window
- MiMo-V2.5
- Best: 1M
- G9v3-39A5B
- 131K
Reasoning
- MiMo-V2.5
- Yes
- G9v3-39A5B
- Yes
Open weights
- MiMo-V2.5
- Yes
- G9v3-39A5B
- Yes
Cost / task
- MiMo-V2.5
- $0.0191
- G9v3-39A5B
- —
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- MiMo-V2.521.8 · $0.0191
Not plotted for lack of data on these axes: G9v3-39A5B.