SShogo Bench

Claude Sonnet 4

Balanced Claude model for coding, analysis, agent workflows, and cost control

Shogo Agent Index

Supported#78 of 92
26.2range 19.5–33 · 28% of weight measured
Agentic coding
26
11% measured
Long-horizon autonomy
36
50% measured
Knowledge-work agents
23
20% measured
Computer use
19
40% measured
Security & context learning
25
50% measured

Price

Input
$2.60/M
Output
$13.00/M
Cache read
$0.26/M
3:1 blend
$5.20/M
Agent-effective
$1.20/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 61
Terminal-Bench 2.0est.8%predicted 23
DeepSWEest.6%predicted 18
FrontierSWEest.5%predicted 2
CursorBenchest.4%predicted 23
GSO-Bench4.9%4%OpenHands
METR Time Horizons62.0%10%source
Vending-Bench 2est.6%predicted 7
PostTrainBenchest.4%predicted 15
APEX-Agentsest.8%predicted 19
GDPvalest.7%predicted 25
Remote Labor Indexest.5%predicted 1
DeepResearch Bench46.6%5%source
OSWorld 2.0est.6%predicted 2
OSWorld43.9%4%claude-4-sonnet-20250514 (50 steps)
Cybench35.0%5%source
CL-benchest.5%predicted 15

Other benchmarks

BenchmarkCategoryScoreSource
Aider PolyglotCoding61.3%source
ARC-AGIReasoning40.0%source
ARC-AGI-2Reasoning5.9%source
CritPtReasoning0.3%source
DTBenchKnowledge77.1%source
Fiction.LiveBenchLong context46.9%source
GeoBenchMultimodal37.0%source
GPQA DiamondReasoning79.2%source
Humanity's Last ExamReasoning7.8%source
LMCAKnowledge29.0%source
MATH Level 5Math84.4%source
OTIS Mock AIMEMath71.1%source
SciCodeCoding40.0%source
SimpleBenchReasoning45.5%source
TheAgentCompanyKnowledge work33.1%source
VPCTMultimodal34.0%source