SShogo Bench

Gemini 2.5 Flash

Fast Gemini workhorse for multimodal apps where latency and price matter

Shogo Agent Index

Estimated#84 of 92
23.6range 15.5–31.8 · 14% of weight measured
Agentic coding
24
23% measured
Long-horizon autonomy
33
30% measured
Knowledge-work agents
21
estimated
Computer use
13
estimated
Security & context learning
24
estimated

Price

Input
$0.30/M
Output
$2.50/M
Cache read
$0.030/M
3:1 blend
$0.85/M
Agent-effective
$0.19/M

Cheapest host for agents: Google AI Studio at $0.090/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 59
Terminal-Bench 2.017.1%8% Mini-SWE-Agent
DeepSWEest.6%predicted 16
FrontierSWEest.5%predicted 2
CursorBenchest.4%predicted 22
GSO-Benchest.4%predicted 4
METR Time Horizonsest.10%predicted 58
Vending-Bench 2$5496%source
PostTrainBenchest.4%predicted 14
APEX-Agentsest.8%predicted 17
GDPvalest.7%predicted 24
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 43
OSWorld 2.0est.6%predicted 1
OSWorldest.4%predicted 30
Cybenchest.5%predicted 34
CL-benchest.5%predicted 15

Other benchmarks

BenchmarkCategoryScoreSource
Aider PolyglotCoding55.1%source
ARC-AGIReasoning33.3%source
ARC-AGI-2Reasoning2.5%source
BALROGLong-horizon33.5%source
CritPtReasoning1.1%source
DTBenchKnowledge76.5%source
Fiction.LiveBenchLong context77.8%source
GeoBenchMultimodal76.0%source
Humanity's Last ExamReasoning12.1%source
LMCAKnowledge27.5%source
OTIS Mock AIMEMath73.1%source
SimpleBenchReasoning41.2%source
TheAgentCompanyKnowledge work41.1%source
VPCTMultimodal46.2%source

API hosts

Live prices and uptime for every host serving Gemini 2.5 Flash via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Google AI Studio$0.15$1.25$0.015$0.09099.6%—
Google AI Studio$0.30$2.50$0.030$0.19100.0%—
Google AI Studio$0.54$4.50$0.054$0.3497.2%—