SShogo Bench

o3-pro

High-effort o3 tier for difficult technical reasoning and careful answers

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
36
estimated
Long-horizon autonomy
43
estimated
Knowledge-work agents
28
estimated
Computer use
23
estimated
Security & context learning
36
estimated

Price

Input
$18.18/M
Output
$72.73/M
Cache read
—/M
3:1 blend
$31.82/M
Agent-effective
$20.78/M

Cheapest host for agents: OpenAI at $22.86/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 69
Terminal-Bench 2.0est.8%predicted 43
DeepSWEest.6%predicted 29
FrontierSWEest.5%predicted 6
CursorBenchest.4%predicted 29
GSO-Benchest.4%predicted 11
METR Time Horizonsest.10%predicted 67
Vending-Bench 2est.6%predicted 18
PostTrainBenchest.4%predicted 19
APEX-Agentsest.8%predicted 29
GDPvalest.7%predicted 34
Remote Labor Indexest.5%predicted 2
DeepResearch Benchest.5%predicted 45
OSWorld 2.0est.6%predicted 3
OSWorldest.4%predicted 52
Cybenchest.5%predicted 54
CL-benchest.5%predicted 18

Other benchmarks

BenchmarkCategoryScoreSource
Aider PolyglotCoding84.9%source
ARC-AGIReasoning59.3%source
ARC-AGI-2Reasoning4.9%source
DTBenchKnowledge86.9%source
Fiction.LiveBenchLong context97.2%source
LMCAKnowledge38.5%source

API hosts

Live prices and uptime for every host serving o3-pro via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
OpenAI$20.00$80.00—$22.86100.0%—