SShogo Bench

GPT-5.4 nano

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

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
34
estimated
Long-horizon autonomy
41
estimated
Knowledge-work agents
27
estimated
Computer use
21
estimated
Security & context learning
34
estimated

Price

Input
$0.20/M
Output
$1.25/M
Cache read
$0.020/M
3:1 blend
$0.46/M
Agent-effective
$0.10/M

Cheapest host for agents: OpenAI at $0.050/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 67
Terminal-Bench 2.0est.8%predicted 38
DeepSWEest.6%predicted 27
FrontierSWEest.5%predicted 5
CursorBenchest.4%predicted 28
GSO-Benchest.4%predicted 10
METR Time Horizonsest.10%predicted 65
Vending-Bench 2est.6%predicted 15
PostTrainBenchest.4%predicted 18
APEX-Agentsest.8%predicted 26
GDPvalest.7%predicted 32
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 45
OSWorld 2.0est.6%predicted 3
OSWorldest.4%predicted 48
Cybenchest.5%predicted 50
CL-benchest.5%predicted 17

Other benchmarks

BenchmarkCategoryScoreSource
ARC-AGIReasoning51.5%source
ARC-AGI-2Reasoning5.7%source
Chess PuzzlesReasoning45.0%source
CritPtReasoning9.3%source
DTBenchKnowledge80.3%source
FrontierMath Tiers 1-3Math44.9%source
FrontierMath Tier 4Math12.2%source
GPQA DiamondReasoning78.5%source
LMCAKnowledge36.9%source
OTIS Mock AIMEMath87.8%source
ProofBenchMath5.0%source
SciCodeCoding47.2%source
SimpleQA VerifiedKnowledge11.7%source

API hosts

Live prices and uptime for every host serving GPT-5.4 nano via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
OpenAI$0.10$0.63$0.010$0.050100.0%—
Azure$0.20$1.25$0.020$0.10100.0%—
OpenAI$0.20$1.25$0.020$0.10100.0%—