Model Comparator
Compare up to four models using the same criteria.
2 models compared
- MiniMax-M2.5
MiniMax
- Qwen3.5 27B (Reasoning)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | MiniMax-M2.5 MiniMax | Qwen3.5 27B (Reasoning) Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 22.8 | Best: 22.9 | |
| Speed | 66.9 t/s | Best: 77.3 t/s | |
| TTFT | Best: 1.46 s | 5.72 s | |
| Input · $ / 1M tokens | $0.30 | $0.30 | |
| Output · $ / 1M tokens | Best: $1.20 | $2.40×2 relative to the lowest price among the compared models | |
| Context window | 205K | Best: 262K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- MiniMax-M2.5
- 22.8
- Qwen3.5 27B (Reasoning)
- Best: 22.9
Speed
- MiniMax-M2.5
- 66.9 t/s
- Qwen3.5 27B (Reasoning)
- Best: 77.3 t/s
TTFT
- MiniMax-M2.5
- Best: 1.46 s
- Qwen3.5 27B (Reasoning)
- 5.72 s
Input · $ / 1M tokens
- MiniMax-M2.5
- $0.30
- Qwen3.5 27B (Reasoning)
- $0.30
Output · $ / 1M tokens
- MiniMax-M2.5
- Best: $1.20
- Qwen3.5 27B (Reasoning)
- $2.40×2 relative to the lowest price among the compared models
Context window
- MiniMax-M2.5
- 205K
- Qwen3.5 27B (Reasoning)
- Best: 262K
Reasoning
- MiniMax-M2.5
- Yes
- Qwen3.5 27B (Reasoning)
- Yes
Open weights
- MiniMax-M2.5
- Yes
- Qwen3.5 27B (Reasoning)
- Yes
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.
- MiniMax-M2.522.8 · $0.525
- Qwen3.5 27B (Reasoning)22.9 · $0.825