SShogo Bench

DeepSeek-R1-Distill-Qwen-14B

DeepSeek-R1-Distill-Qwen-14B from DeepSeek.

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
15
estimated
Long-horizon autonomy
26
estimated
Knowledge-work agents
15
estimated
Computer use
5
estimated
Security & context learning
14
estimated

Price

No public API price.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 46
Terminal-Bench 2.0est.8%predicted 6
DeepSWEest.6%predicted 7
FrontierSWEest.5%predicted 1
CursorBenchest.4%predicted 16
GSO-Benchest.4%predicted 1
METR Time Horizonsest.10%predicted 47
Vending-Bench 2est.6%predicted 1
PostTrainBenchest.4%predicted 10
APEX-Agentsest.8%predicted 9
GDPvalest.7%predicted 15
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 40
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 12
Cybenchest.5%predicted 16
CL-benchest.5%predicted 12

Other benchmarks

BenchmarkCategoryScoreSource
GPQA DiamondReasoning44.7%source
MATH Level 5Math87.1%source
OTIS Mock AIMEMath50.6%source