SShogo Bench

Mistral Large 3

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

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
16
estimated
Long-horizon autonomy
27
estimated
Knowledge-work agents
15
estimated
Computer use
6
estimated
Security & context learning
15
estimated

Price

Input
$1.10/M
Output
$3.30/M
Cache read
—/M
3:1 blend
$1.65/M
Agent-effective
$1.20/M

Cheapest host for agents: Mistral at $0.18/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 48
Terminal-Bench 2.0est.8%predicted 7
DeepSWEest.6%predicted 8
FrontierSWEest.5%predicted 1
CursorBenchest.4%predicted 16
GSO-Benchest.4%predicted 1
METR Time Horizonsest.10%predicted 48
Vending-Bench 2est.6%predicted 2
PostTrainBenchest.4%predicted 10
APEX-Agentsest.8%predicted 9
GDPvalest.7%predicted 15
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 41
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 13
Cybenchest.5%predicted 17
CL-benchest.5%predicted 12

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning0.0%source
DTBenchKnowledge65.1%source
LMCAKnowledge16.7%source
SciCodeCoding36.6%source
SimpleBenchReasoning20.4%source
WebDev ArenaCoding1230source

API hosts

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

HostInputOutputCache readAgent $/MUptime 24hQuant
Mistral$0.50$1.50$0.050$0.1899.9%—
Mistral$0.55$1.65$0.055$0.2099.7%—