SShogo Bench

o4-mini

Fast o-series model for compact reasoning, coding, and tool use

Shogo Agent Index

Estimated#73 of 92
29.8range 19.2–40.4 · 21% of weight measured
Agentic coding
31
11% measured
Long-horizon autonomy
39
50% measured
Knowledge-work agents
24
28% measured
Computer use
19
estimated
Security & context learning
32
estimated

Price

Input
$0.99/M
Output
$4.00/M
Cache read
$0.25/M
3:1 blend
$1.74/M
Agent-effective
$0.53/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 66
Terminal-Bench 2.0est.8%predicted 34
DeepSWEest.6%predicted 24
FrontierSWEest.5%predicted 4
CursorBenchest.4%predicted 26
GSO-Bench3.6%4%OpenHands
METR Time Horizons63.9%10%source
Vending-Bench 2est.6%predicted 13
PostTrainBenchest.4%predicted 17
APEX-Agentsest.8%predicted 24
GDPval25.3%7%source
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 45
OSWorld 2.0est.6%predicted 2
OSWorldest.4%predicted 44
Cybenchest.5%predicted 47
CL-benchest.5%predicted 17

Other benchmarks

BenchmarkCategoryScoreSource
Aider PolyglotCoding72.0%source
AlgoTuneCoding1.72×source
ARC-AGIReasoning58.7%source
ARC-AGI-2Reasoning6.1%source
Chess PuzzlesReasoning22.0%source
CritPtReasoning0.6%source
DTBenchKnowledge77.6%source
Fiction.LiveBenchLong context77.8%source
FrontierMath Tiers 1-3Math36.1%source
FrontierMath Tier 4Math4.9%source
GeoBenchMultimodal64.0%source
GPQA DiamondReasoning79.6%source
Humanity's Last ExamReasoning18.1%source
LMCAKnowledge26.5%source
MATH Level 5Math97.8%source
OTIS Mock AIMEMath81.7%source
SimpleBenchReasoning38.7%source
SimpleQA VerifiedKnowledge19.6%source
VPCTMultimodal57.5%source