SShogo Bench

GPT-5.2 Codex

Code-specialist GPT for repository edits, reviews, and long-running software agents

Shogo Agent Index

Unranked

Not ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.

Agentic coding
45
23% measured
Long-horizon autonomy
48
estimated
Knowledge-work agents
32
estimated
Computer use
28
estimated
Security & context learning
41
estimated

Price

Input
$1.60/M
Output
$13.00/M
Cache read
$0.16/M
3:1 blend
$4.45/M
Agent-effective
$0.98/M

Cheapest host for agents: Azure at $1.06/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 72
Terminal-Bench 2.066.5%8%Deep Agents
DeepSWEest.6%predicted 36
FrontierSWEest.5%predicted 9
CursorBenchest.4%predicted 32
GSO-Benchest.4%predicted 17
METR Time Horizonsest.10%predicted 70
Vending-Bench 2est.6%predicted 28
PostTrainBenchest.4%predicted 21
APEX-Agentsest.8%predicted 34
GDPvalest.7%predicted 39
Remote Labor Indexest.5%predicted 2
DeepResearch Benchest.5%predicted 46
OSWorld 2.0est.6%predicted 5
OSWorldest.4%predicted 62
Cybenchest.5%predicted 63
CL-benchest.5%predicted 19

Other benchmarks

BenchmarkCategoryScoreSource
WebDev ArenaCoding1339source

API hosts

Live prices and uptime for every host serving GPT-5.2 Codex via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Azure$1.75$14.00$0.17$1.06100.0%—