MiMo-V2.5-Pro
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution
Shogo Agent Index
UnrankedNot ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
39
estimated
Long-horizon autonomy
45
estimated
Knowledge-work agents
30
estimated
Computer use
25
estimated
Security & context learning
38
estimated
Price
- Input
- $0.43/M
- Output
- $0.87/M
- Cache read
- $0.004/M
- 3:1 blend
- $0.54/M
- Agent-effective
- $0.11/M
Cheapest host for agents: DigitalOcean at $0.23/M.
Agent-effective = 20 input tokens per output token, 85% cache hits. Why.
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 70 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 48 | |
| DeepSWE | est. | 6% | predicted 32 | |
| FrontierSWE | est. | 5% | predicted 7 | |
| CursorBench | est. | 4% | predicted 30 | |
| GSO-Bench | est. | 4% | predicted 13 | |
| METR Time Horizons | est. | 10% | predicted 68 | |
| Vending-Bench 2 | est. | 6% | predicted 22 | |
| PostTrainBench | est. | 4% | predicted 20 | |
| APEX-Agents | est. | 8% | predicted 31 | |
| GDPval | est. | 7% | predicted 36 | |
| Remote Labor Index | est. | 5% | predicted 2 | |
| DeepResearch Bench | est. | 5% | predicted 46 | |
| OSWorld 2.0 | est. | 6% | predicted 4 | |
| OSWorld | est. | 4% | predicted 57 | |
| Cybench | est. | 5% | predicted 58 | |
| CL-bench | est. | 5% | predicted 18 |
Other benchmarks
API hosts
Live prices and uptime for every host serving MiMo-V2.5-Pro via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| DigitalOcean | $0.48 | $1.80 | $0.096 | $0.23 | 94.3% | — |