SShogo Bench

Claude Opus 4.1 (latest)

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Shogo Agent Index

Supported#66 of 92
32.1range 25.4–38.8 · 43% of weight measured
Agentic coding
34
46% measured
Long-horizon autonomy
40
50% measured
Knowledge-work agents
30
48% measured
Computer use
19
estimated
Security & context learning
29
50% measured

Price

Input
$13.00/M
Output
$64.00/M
Cache read
$1.30/M
3:1 blend
$25.75/M
Agent-effective
$5.96/M

Cheapest host for agents: Amazon Bedrock at $6.93/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verified73.3%8%source
Terminal-Bench 2.038.0%8% Terminus 2
DeepSWEest.6%predicted 23
FrontierSWEest.5%predicted 4
CursorBenchest.4%predicted 26
GSO-Benchest.4%predicted 8
METR Time Horizons66.8%10%source
Vending-Bench 2est.6%predicted 12
PostTrainBenchest.4%predicted 17
APEX-Agentsest.8%predicted 24
GDPval43.6%7%source
Remote Labor Indexest.5%predicted 1
DeepResearch Bench48.3%5%source
OSWorld 2.0est.6%predicted 2
OSWorldest.4%predicted 43
Cybench42.0%5%source
CL-benchest.5%predicted 17

Other benchmarks

BenchmarkCategoryScoreSource
AlgoTuneCoding1.34×source
DTBenchKnowledge80.0%source
FrontierMath Tiers 1-3Math12.6%source
FrontierMath Tier 4Math2.4%source
GPQA DiamondReasoning77.3%source
Humanity's Last ExamReasoning11.5%source
LMCAKnowledge37.1%source
OTIS Mock AIMEMath68.9%source
SimpleBenchReasoning60.0%source
VPCTMultimodal35.0%source
WebDev ArenaCoding1389source

API hosts

Live prices and uptime for every host serving Claude Opus 4.1 (latest) via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Amazon Bedrock$15.00$75.00$1.50$6.93100.0%—