SShogo Bench

DeepSeek-V3

Open DeepSeek MoE chat model for coding, math, and general reasoning

Shogo Agent Index

Unranked

Not ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.

Agentic coding
14
estimated
Long-horizon autonomy
26
50% measured
Knowledge-work agents
14
estimated
Computer use
4
estimated
Security & context learning
13
estimated

Price

Input
$0.29/M
Output
$1.16/M
Cache read
—/M
3:1 blend
$0.51/M
Agent-effective
$0.33/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 45
Terminal-Bench 2.0est.8%predicted 5
DeepSWEest.6%predicted 7
FrontierSWEest.5%predicted 1
CursorBenchest.4%predicted 15
GSO-Benchest.4%predicted 1
METR Time Horizons47.4%10%source
Vending-Bench 2est.6%predicted 1
PostTrainBenchest.4%predicted 10
APEX-Agentsest.8%predicted 8
GDPvalest.7%predicted 14
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 40
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 10
Cybenchest.5%predicted 14
CL-benchest.5%predicted 11

Other benchmarks

BenchmarkCategoryScoreSource
Aider PolyglotCoding48.4%source
CritPtReasoning0.0%source
GPQA DiamondReasoning56.5%source
MATH Level 5Math64.9%source
MMLULegacy87.2%source
OTIS Mock AIMEMath15.8%source
SciCodeCoding35.8%source
SimpleBenchReasoning18.9%source