SShogo Bench

GPT-6.2 Astra

A frontier reasoning model for coding, computer use, and professional work such as slides, spreadsheets, and documents.

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
88
estimated
Long-horizon autonomy
84
estimated
Knowledge-work agents
67
estimated
Computer use
79
estimated
Security & context learning
66
estimated

Price

Input
$8.00/M
Output
$40.00/M
Cache read
$0.40/M
3:1 blend
$16.00/M
Agent-effective
$3.37/M

Cheapest host for agents: Amazon Bedrock at $3.37/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 92
Terminal-Bench 2.0est.8%predicted 98
DeepSWEest.6%predicted 89
FrontierSWEest.5%predicted 79
CursorBenchest.4%predicted 63
GSO-Benchest.4%predicted 89
METR Time Horizonsest.10%predicted 90
Vending-Bench 2est.6%predicted 97
PostTrainBenchest.4%predicted 46
APEX-Agentsest.8%predicted 84
GDPvalest.7%predicted 79
Remote Labor Indexest.5%predicted 36
DeepResearch Benchest.5%predicted 55
OSWorld 2.0est.6%predicted 66
OSWorldest.4%predicted 98
Cybenchest.5%predicted 97
CL-benchest.5%predicted 35

Other benchmarks

BenchmarkCategoryScoreSource
Chess PuzzlesReasoning78.0%source
FrontierMath Tiers 1-3Math92.6%source
FrontierMath Tier 4Math100.0%source
GPQA DiamondReasoning96.8%source
MirrorCodeCoding67.8%source
OTIS Mock AIMEMath100.0%source
SimpleQA VerifiedKnowledge78.5%source

API hosts

Live prices and uptime for every host serving GPT-6.2 Astra via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Amazon Bedrock$8.00$40.00$0.40$3.3799.9%—
Azure$8.00$40.00$0.40$3.37100.0%—
OpenAI$8.00$40.00$0.40$3.3799.9%—
OpenAI$16.00$80.00$0.80$6.74100.0%—
OpenAI$24.00$120.00$1.20$10.11100.0%—