SShogo Bench

Qwen3.5 4B

Qwen instruction model for multilingual chat and tool use

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
19
estimated
Long-horizon autonomy
29
estimated
Knowledge-work agents
17
estimated
Computer use
8
estimated
Security & context learning
18
estimated

Price

Input
Free/M
Output
Free/M
Cache read
—/M
3:1 blend
Free/M
Agent-effective
Free/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 52
Terminal-Bench 2.0est.8%predicted 10
DeepSWEest.6%predicted 11
FrontierSWEest.5%predicted 1
CursorBenchest.4%predicted 18
GSO-Benchest.4%predicted 2
METR Time Horizonsest.10%predicted 52
Vending-Bench 2est.6%predicted 3
PostTrainBenchest.4%predicted 12
APEX-Agentsest.8%predicted 12
GDPvalest.7%predicted 18
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 42
OSWorld 2.0est.6%predicted 1
OSWorldest.4%predicted 18
Cybenchest.5%predicted 23
CL-benchest.5%predicted 13

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning0.0%source
OTIS Mock AIMEMath55.8%source