SShogo Bench

Mistral Nemo

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

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
6
estimated
Long-horizon autonomy
13
estimated
Knowledge-work agents
8
estimated
Computer use
0
estimated
Security & context learning
4
estimated

Price

Input
$0.16/M
Output
$0.18/M
Cache read
$0.16/M
3:1 blend
$0.16/M
Agent-effective
$0.16/M

Cheapest host for agents: Io Net at $0.010/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 21
Terminal-Bench 2.0est.8%predicted 0
DeepSWEest.6%predicted 1
FrontierSWEest.5%predicted 0
CursorBenchest.4%predicted 6
GSO-Benchest.4%predicted 0
METR Time Horizonsest.10%predicted 24
Vending-Bench 2est.6%predicted 0
PostTrainBenchest.4%predicted 4
APEX-Agentsest.8%predicted 2
GDPvalest.7%predicted 4
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 34
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 1
Cybenchest.5%predicted 2
CL-benchest.5%predicted 7

Other benchmarks

BenchmarkCategoryScoreSource
BALROGLong-horizon17.6%source
DTBenchKnowledge48.6%source
GPQA DiamondReasoning29.9%source
MATH Level 5Math10.8%source

API hosts

Live prices and uptime for every host serving Mistral Nemo via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Io Net$0.017$0.022$0.011$0.01099.9%fp16
DeepInfra$0.023$0.024—$0.02098.0%fp8
DekaLLM$0.018$0.030—$0.02090.6%fp8
DeepInfra$0.029$0.030—$0.030100.0%fp8
Parasail$0.030$0.030—$0.03086.9%fp8
Mistral$0.15$0.15$0.015$0.040100.0%—