SShogo Bench

Gemini 3 Deep Think

Gemini 3 Deep Think from Google.

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
70
estimated
Long-horizon autonomy
72
estimated
Knowledge-work agents
50
estimated
Computer use
52
estimated
Security & context learning
58
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 85
Terminal-Bench 2.0est.8%predicted 91
DeepSWEest.6%predicted 70
FrontierSWEest.5%predicted 39
CursorBenchest.4%predicted 48
GSO-Benchest.4%predicted 58
METR Time Horizonsest.10%predicted 83
Vending-Bench 2est.6%predicted 81
PostTrainBenchest.4%predicted 33
APEX-Agentsest.8%predicted 63
GDPvalest.7%predicted 62
Remote Labor Indexest.5%predicted 11
DeepResearch Benchest.5%predicted 51
OSWorld 2.0est.6%predicted 26
OSWorldest.4%predicted 91
Cybenchest.5%predicted 89
CL-benchest.5%predicted 27

Other benchmarks

BenchmarkCategoryScoreSource
ARC-AGIReasoning96.0%source
ARC-AGI-2Reasoning84.6%source
CritPtReasoning25.7%source