SShogo Bench

Inkling Small

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

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
43
estimated
Long-horizon autonomy
49
estimated
Knowledge-work agents
32
estimated
Computer use
29
estimated
Security & context learning
42
estimated

Price

Input
$0.58/M
Output
$1.44/M
Cache read
$0.12/M
3:1 blend
$0.80/M
Agent-effective
$0.25/M

Cheapest host for agents: DeepInfra at $0.20/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 2.0est.8%predicted 56
DeepSWEest.6%predicted 38
FrontierSWEest.5%predicted 9
CursorBenchest.4%predicted 33
GSO-Benchest.4%predicted 18
METR Time Horizonsest.10%predicted 71
Vending-Bench 2est.6%predicted 30
PostTrainBenchest.4%predicted 21
APEX-Agentsest.8%predicted 35
GDPvalest.7%predicted 40
Remote Labor Indexest.5%predicted 2
DeepResearch Benchest.5%predicted 47
OSWorld 2.0est.6%predicted 5
OSWorldest.4%predicted 64
Cybenchest.5%predicted 64
CL-benchest.5%predicted 20

Other benchmarks

BenchmarkCategoryScoreSource
ARC-AGIReasoning84.0%source
ARC-AGI-2Reasoning40.1%source
CritPtReasoning8.3%source
FrontierMath Tiers 1-3Math46.3%source
FrontierMath Tier 4Math17.1%source
GPQA DiamondReasoning88.5%source
OTIS Mock AIMEMath90.0%source
ProofBenchMath6.0%source
SciCodeCoding49.7%source
SimpleQA VerifiedKnowledge19.1%source
WebDev ArenaCoding1407source

API hosts

Live prices and uptime for every host serving Inkling Small via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
DeepInfra$0.45$1.20$0.10$0.20100.0%fp4