Model Comparator
Compare up to four models using the same criteria.
2 models compared
- MiniMax-M3
MiniMax
- KAT-Coder-Pro V1
KwaiKAT
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | MiniMax-M3 MiniMax | KAT-Coder-Pro V1 KwaiKAT | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 18.9 | 18.6 | |
| Coding | 58.6 | — | |
| Math | — | 94.7 | |
| Agentic | 29.5 | — | |
| Cyber Index | 22.4% | — | |
| Speed | 96.9 t/s | — | |
| TTFT | 0.89 s | — | |
| Input · $ / 1M tokens | $0.30 | — | |
| Output · $ / 1M tokens | $1.20 | — | |
| Context window | Best: 1M | 256K | |
| Reasoning | Yes | No | |
| Open weights | Yes | No | |
| Cost / task | $1.29 | — |
Intelligence
- MiniMax-M3
- Best: 18.9
- KAT-Coder-Pro V1
- 18.6
Coding
- MiniMax-M3
- 58.6
- KAT-Coder-Pro V1
- —
Math
- MiniMax-M3
- —
- KAT-Coder-Pro V1
- 94.7
Agentic
- MiniMax-M3
- 29.5
- KAT-Coder-Pro V1
- —
Cyber Index
- MiniMax-M3
- 22.4%
- KAT-Coder-Pro V1
- —
Speed
- MiniMax-M3
- 96.9 t/s
- KAT-Coder-Pro V1
- —
TTFT
- MiniMax-M3
- 0.89 s
- KAT-Coder-Pro V1
- —
Input · $ / 1M tokens
- MiniMax-M3
- $0.30
- KAT-Coder-Pro V1
- —
Output · $ / 1M tokens
- MiniMax-M3
- $1.20
- KAT-Coder-Pro V1
- —
Context window
- MiniMax-M3
- Best: 1M
- KAT-Coder-Pro V1
- 256K
Reasoning
- MiniMax-M3
- Yes
- KAT-Coder-Pro V1
- No
Open weights
- MiniMax-M3
- Yes
- KAT-Coder-Pro V1
- No
Cost / task
- MiniMax-M3
- $1.29
- KAT-Coder-Pro V1
- —
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-M318.9 · $1.29
Not plotted for lack of data on these axes: KAT-Coder-Pro V1.