SShogo Bench

Mistral Small 3

Efficient Mistral model for fast chat, extraction, and production assistants

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
10
estimated
Long-horizon autonomy
19
estimated
Knowledge-work agents
11
estimated
Computer use
2
estimated
Security & context learning
8
estimated

Price

Input
$0.053/M
Output
$0.085/M
Cache read
—/M
3:1 blend
$0.060/M
Agent-effective
$0.050/M

Cheapest host for agents: DeepInfra at $0.040/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 33
Terminal-Bench 2.0est.8%predicted 1
DeepSWEest.6%predicted 3
FrontierSWEest.5%predicted 0
CursorBenchest.4%predicted 10
GSO-Benchest.4%predicted 0
METR Time Horizonsest.10%predicted 35
Vending-Bench 2est.6%predicted 0
PostTrainBenchest.4%predicted 7
APEX-Agentsest.8%predicted 4
GDPvalest.7%predicted 8
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 37
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 4
Cybenchest.5%predicted 6
CL-benchest.5%predicted 9

Other benchmarks

BenchmarkCategoryScoreSource
GPQA DiamondReasoning47.3%source
MATH Level 5Math44.8%source
OTIS Mock AIMEMath6.7%source

API hosts

Live prices and uptime for every host serving Mistral Small 3 via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
DeepInfra$0.040$0.064—$0.040—fp8
DeepInfra$0.050$0.080—$0.050100.0%fp8