SShogo Bench

o3-mini

Smaller o-series reasoner for economical coding, math, and planning tasks

Shogo Agent Index

Estimated#85 of 92
23.3range 14.9–31.6 · 9% of weight measured
Agentic coding
24
11% measured
Long-horizon autonomy
34
estimated
Knowledge-work agents
21
estimated
Computer use
13
estimated
Security & context learning
19
50% measured

Price

Input
$0.99/M
Output
$4.00/M
Cache read
—/M
3:1 blend
$1.74/M
Agent-effective
$1.13/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 59
Terminal-Bench 2.0est.8%predicted 19
DeepSWEest.6%predicted 16
FrontierSWEest.5%predicted 2
CursorBenchest.4%predicted 22
GSO-Bench1.3%4%OpenHands
METR Time Horizonsest.10%predicted 58
Vending-Bench 2est.6%predicted 6
PostTrainBenchest.4%predicted 14
APEX-Agentsest.8%predicted 17
GDPvalest.7%predicted 23
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 43
OSWorld 2.0est.6%predicted 1
OSWorldest.4%predicted 29
Cybench22.5%5%source
CL-benchest.5%predicted 15

Other benchmarks

BenchmarkCategoryScoreSource
Aider PolyglotCoding60.4%source
ARC-AGIReasoning34.5%source
ARC-AGI-2Reasoning3.0%source
Chess PuzzlesReasoning15.0%source
CritPtReasoning0.3%source
DTBenchKnowledge68.8%source
Fiction.LiveBenchLong context50.0%source
FrontierMath Tiers 1-3Math18.6%source
FrontierMath Tier 4Math0.0%source
GPQA DiamondReasoning77.0%source
LMCAKnowledge19.0%source
MATH Level 5Math96.5%source
OTIS Mock AIMEMath76.9%source
SciCodeCoding42.8%source
SimpleBenchReasoning22.8%source
SimpleQA VerifiedKnowledge15.3%source