Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3.6 27B (Reasoning)
Alibaba
- MiMo-V2.5
Xiaomi
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3.6 27B (Reasoning) Alibaba | MiMo-V2.5 Xiaomi | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 21.4 | Best: 21.8 | |
| Coding | 53.7 | Best: 56.8 | |
| Agentic | Best: 18.5 | 15.8 | |
| Speed | Best: 55.6 t/s | 33.3 t/s | |
| TTFT | Best: 3.68 s | 5.88 s | |
| Input · $ / 1M tokens | $0.60×4.3 relative to the lowest price among the compared models | Best: $0.14 | |
| Output · $ / 1M tokens | $3.60×12.9 relative to the lowest price among the compared models | Best: $0.28 | |
| Context window | 262K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.621×32.5 relative to the lowest price among the compared models | Best: $0.0191 |
Intelligence
- Qwen3.6 27B (Reasoning)
- 21.4
- MiMo-V2.5
- Best: 21.8
Coding
- Qwen3.6 27B (Reasoning)
- 53.7
- MiMo-V2.5
- Best: 56.8
Agentic
- Qwen3.6 27B (Reasoning)
- Best: 18.5
- MiMo-V2.5
- 15.8
Speed
- Qwen3.6 27B (Reasoning)
- Best: 55.6 t/s
- MiMo-V2.5
- 33.3 t/s
TTFT
- Qwen3.6 27B (Reasoning)
- Best: 3.68 s
- MiMo-V2.5
- 5.88 s
Input · $ / 1M tokens
- Qwen3.6 27B (Reasoning)
- $0.60×4.3 relative to the lowest price among the compared models
- MiMo-V2.5
- Best: $0.14
Output · $ / 1M tokens
- Qwen3.6 27B (Reasoning)
- $3.60×12.9 relative to the lowest price among the compared models
- MiMo-V2.5
- Best: $0.28
Context window
- Qwen3.6 27B (Reasoning)
- 262K
- MiMo-V2.5
- Best: 1M
Reasoning
- Qwen3.6 27B (Reasoning)
- Yes
- MiMo-V2.5
- Yes
Open weights
- Qwen3.6 27B (Reasoning)
- Yes
- MiMo-V2.5
- Yes
Cost / task
- Qwen3.6 27B (Reasoning)
- $0.621×32.5 relative to the lowest price among the compared models
- MiMo-V2.5
- Best: $0.0191
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.
- Qwen3.6 27B (Reasoning)21.4 · $0.621
- MiMo-V2.521.8 · $0.0191