Kimi K2.5 vs Mistral Small 3.1 24B Base
Moonshot AI vs Mistral AI — benchmarks, pricing, and capabilities side by side.
- •Kimi K2.5 has the higher intelligence index (87.9 vs 50.9)
- •Mistral Small 3.1 24B Base is cheaper ($0.10 vs $0.40 per 1M input)
- •Mistral Small 3.1 24B Base is faster
- •Kimi K2.5 has a larger context window (262K)
| Kimi K2.5 | Mistral Small 3.1 24B Base | |
|---|---|---|
| Intelligence index | 87.9 | 50.9 |
| Developer | Moonshot AI | Mistral AI |
| Type | Multimodal | Multimodal |
| Access | Open weights | Open weights |
| Context window | 262,144 tokens | 128,000 tokens |
| Input price | $0.40 / 1M | $0.10 / 1M |
| Output price | $1.90 / 1M | $0.30 / 1M |
| Speed | 35 tok/s | 137 tok/s |
| Released | January 27, 2026 | March 17, 2025 |
| Parameters | 1T (32B active) | 24000000000 |
| Input modalities | Text, Image | — |
| Output modalities | Text | — |
Shared benchmarks
Kimi K2.5
Mistral Small 3.1 24B Base
GPQA Diamond
87.9
37.5