SShogo Bench

GPT-5.1 Codex Max

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Shogo Agent Index

Estimated#56 of 92
39.6range 26.4–52.9 · 18% of weight measured
Agentic coding
43
23% measured
Long-horizon autonomy
48
50% measured
Knowledge-work agents
32
estimated
Computer use
28
estimated
Security & context learning
41
estimated

Price

Input
$1.10/M
Output
$9.00/M
Cache read
$0.11/M
3:1 blend
$3.08/M
Agent-effective
$0.67/M

Cheapest host for agents: Azure at $0.76/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 73
Terminal-Bench 2.060.4%8%Codex CLI
DeepSWEest.6%predicted 36
FrontierSWEest.5%predicted 9
CursorBenchest.4%predicted 32
GSO-Benchest.4%predicted 17
METR Time Horizons70.8%10%source
Vending-Bench 2est.6%predicted 28
PostTrainBenchest.4%predicted 21
APEX-Agentsest.8%predicted 35
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
ProofBenchMath9.0%source

API hosts

Live prices and uptime for every host serving GPT-5.1 Codex Max via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Azure$1.25$10.00$0.13$0.76100.0%—