Updated March 26, 2026· Based on independent benchmark data
MiMo-V2-Pro leads in intelligence with a score of 49.2 vs 46.8. Kimi K2.5 (Reasoning) is 1.7x cheaper at $0.60/1M tokens vs $1.00/1M. For speed, MiMo-V2-Pro wins at 91 tok/s vs 34 tok/s.
| Metric | MiMo-V2-Pro | Kimi K2.5 (Reasoning) |
|---|---|---|
| Intelligence Score | 49.2 | 46.8 |
| Coding Score | 41.4 | 39.5 |
| Math Score | N/A | N/A |
| Speed (tok/s) | 91 tok/s | 34 tok/s |
| Latency (TTFT) | 1.55s | 1.40s |
| Input Price / 1M tokens | $1.00 | $0.60 |
| Output Price / 1M tokens | $3.00 | $3.00 |
| Context Window | N/A |
MiMo-V2-Pro outperforms Kimi K2.5 (Reasoning) on the intelligence index with a score of 49.2 compared to 46.8. Their coding capabilities are closely matched (41.4 vs 39.5).
MiMo-V2-Pro generates output significantly faster at 91 tok/s compared to Kimi K2.5 (Reasoning)'s 34 tok/s, making it 2.7x faster for streaming responses. Time to first token is 1.40s for Kimi K2.5 (Reasoning) vs 1.55s for MiMo-V2-Pro, which affects perceived responsiveness in interactive applications.
Kimi K2.5 (Reasoning) is more affordable at $0.60/1M input tokens ($3.00/1M output), while MiMo-V2-Pro costs $1.00/1M input ($3.00/1M output). For a typical workload of 100 requests per day at 2,000 tokens each, MiMo-V2-Pro would cost approximately $6.00/month vs $3.60/month for Kimi K2.5 (Reasoning) in input costs alone.
Choose MiMo-V2-Pro when you need higher intelligence (49.2), faster output (91 tok/s). Choose Kimi K2.5 (Reasoning) when you need lower cost.
MiMo-V2-Pro scores higher on coding benchmarks (41.4 vs 39.5), making it the better choice for programming tasks.
Kimi K2.5 (Reasoning) is cheaper at $0.60/1M input tokens vs $1.00/1M for MiMo-V2-Pro.
MiMo-V2-Pro is faster, producing output at 91 tok/s compared to Kimi K2.5 (Reasoning)'s 34 tok/s.
No, MiMo-V2-Pro does not support image input. Neither model supports image input.
Data last synced: March 26, 2026
| N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
| Output Modalities | Text | Text |
| Free Tier | No | No |
It depends on your priorities. MiMo-V2-Pro scores higher on intelligence (49.2), but Kimi K2.5 (Reasoning) may be better for specific use cases like budget-conscious projects or speed-critical applications.