SShogo Bench

MiMo-V2.5

Open MiMo model for multimodal coding agents and long-context automation

Shogo Agent Index

Unranked

Not 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

Price

Input
$0.14/M
Output
$0.28/M
Cache read
$0.003/M
3:1 blend
$0.18/M
Agent-effective
$0.040/M

Cheapest host for agents: Venice at $0.22/M.

Agent-effective = 20 input tokens per output token, 85% cache hits. Why.

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 70
Terminal-Bench 2.0est.8%predicted 46
DeepSWEest.6%predicted 31
FrontierSWEest.5%predicted 6
CursorBenchest.4%predicted 30
GSO-Benchest.4%predicted 13
METR Time Horizonsest.10%predicted 68
Vending-Bench 2est.6%predicted 21
PostTrainBenchest.4%predicted 19
APEX-Agentsest.8%predicted 30
GDPvalest.7%predicted 35
Remote Labor Indexest.5%predicted 2
DeepResearch Benchest.5%predicted 46
OSWorld 2.0est.6%predicted 4
OSWorldest.4%predicted 55
Cybenchest.5%predicted 57
CL-benchest.5%predicted 18

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning3.7%source
ProofBenchMath16.0%source
SciCodeCoding43.1%source
WebDev ArenaCoding1437source

API hosts

Live prices and uptime for every host serving MiMo-V2.5 via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Venice$0.40$2.00$0.080$0.2299.7%fp8