SShogo Bench

DeepSeek-R1

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Shogo Agent Index

Estimated#87 of 92
21.1range 13.5–28.6 · 15% of weight measured
Agentic coding
21
estimated
Long-horizon autonomy
31
50% measured
Knowledge-work agents
18
20% measured
Computer use
10
estimated
Security & context learning
21
estimated

Price

Input
$0.50/M
Output
$4.88/M
Cache read
—/M
3:1 blend
$1.59/M
Agent-effective
$0.71/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 56
Terminal-Bench 2.0est.8%predicted 15
DeepSWEest.6%predicted 13
FrontierSWEest.5%predicted 1
CursorBenchest.4%predicted 20
GSO-Benchest.4%predicted 3
METR Time Horizons53.8%10%source
Vending-Bench 2est.6%predicted 4
PostTrainBenchest.4%predicted 13
APEX-Agentsest.8%predicted 15
GDPvalest.7%predicted 21
Remote Labor Indexest.5%predicted 0
DeepResearch Bench35.1%5%source
OSWorld 2.0est.6%predicted 1
OSWorldest.4%predicted 24
Cybenchest.5%predicted 28
CL-benchest.5%predicted 14

Other benchmarks

BenchmarkCategoryScoreSource
Aider PolyglotCoding71.4%source
AlgoTuneCoding1.70×source
ARC-AGIReasoning21.2%source
ARC-AGI-2Reasoning1.3%source
BALROGLong-horizon34.9%source
CritPtReasoning1.1%source
Fiction.LiveBenchLong context75.0%source
GPQA DiamondReasoning76.3%source
MATH Level 5Math96.6%source
OTIS Mock AIMEMath66.4%source
SciCodeCoding38.3%source
SimpleBenchReasoning40.8%source