MiMo-V2.5
Open MiMo model for multimodal coding agents and long-context automation
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
38
estimated
Long-horizon autonomy
44
estimated
Knowledge-work agents
29
estimated
Computer use
25
estimated
Security & context learning
37
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 70 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 46 | |
| DeepSWE | est. | 6% | predicted 31 | |
| FrontierSWE | est. | 5% | predicted 6 | |
| CursorBench | est. | 4% | predicted 30 | |
| GSO-Bench | est. | 4% | predicted 13 | |
| METR Time Horizons | est. | 10% | predicted 68 | |
| Vending-Bench 2 | est. | 6% | predicted 21 | |
| PostTrainBench | est. | 4% | predicted 19 | |
| APEX-Agents | est. | 8% | predicted 30 | |
| GDPval | est. | 7% | predicted 35 | |
| Remote Labor Index | est. | 5% | predicted 2 | |
| DeepResearch Bench | est. | 5% | predicted 46 | |
| OSWorld 2.0 | est. | 6% | predicted 4 | |
| OSWorld | est. | 4% | predicted 55 | |
| Cybench | est. | 5% | predicted 57 | |
| CL-bench | est. | 5% | predicted 18 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| CritPt | Reasoning | 3.7% | source |
| ProofBench | Math | 16.0% | source |
| SciCode | Coding | 43.1% | source |
| WebDev Arena | Coding | 1437 | source |
API hosts
Live prices and uptime for every host serving MiMo-V2.5 via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Venice | $0.40 | $2.00 | $0.080 | $0.22 | 99.7% | fp8 |