SShogo Bench

Qwen3 8B

Dense 8B Qwen3 model with switchable thinking for chat, reasoning, 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
15
estimated
Long-horizon autonomy
25
estimated
Knowledge-work agents
15
estimated
Computer use
5
estimated
Security & context learning
13
estimated

Price

Input
$0.20/M
Output
$0.60/M
Cache read
$0.039/M
3:1 blend
$0.30/M
Agent-effective
$0.090/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 45
Terminal-Bench 2.0est.8%predicted 5
DeepSWEest.6%predicted 7
FrontierSWEest.5%predicted 1
CursorBenchest.4%predicted 15
GSO-Benchest.4%predicted 1
METR Time Horizonsest.10%predicted 46
Vending-Bench 2est.6%predicted 1
PostTrainBenchest.4%predicted 10
APEX-Agentsest.8%predicted 8
GDPvalest.7%predicted 14
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 40
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 11
Cybenchest.5%predicted 15
CL-benchest.5%predicted 11

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning0.0%source
DTBenchKnowledge59.7%source
Fiction.LiveBenchLong context62.1%source
GPQA DiamondReasoning56.8%source
LMCAKnowledge8.8%source
OTIS Mock AIMEMath56.1%source
SciCodeCoding22.6%source