SShogo Bench

Qwen3 30B A3B

Qwen instruction model for multilingual 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
17
estimated
Long-horizon autonomy
27
estimated
Knowledge-work agents
16
estimated
Computer use
6
estimated
Security & context learning
15
estimated

Price

Input
$0.051/M
Output
$0.34/M
Cache read
—/M
3:1 blend
$0.12/M
Agent-effective
$0.060/M

Cheapest host for agents: DeepInfra at $0.11/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 49
Terminal-Bench 2.0est.8%predicted 7
DeepSWEest.6%predicted 9
FrontierSWEest.5%predicted 1
CursorBenchest.4%predicted 17
GSO-Benchest.4%predicted 2
METR Time Horizonsest.10%predicted 49
Vending-Bench 2est.6%predicted 2
PostTrainBenchest.4%predicted 11
APEX-Agentsest.8%predicted 10
GDPvalest.7%predicted 16
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 41
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 14
Cybenchest.5%predicted 18
CL-benchest.5%predicted 12

Other benchmarks

BenchmarkCategoryScoreSource
DTBenchKnowledge60.3%source
Fiction.LiveBenchLong context40.6%source
GPQA DiamondReasoning61.7%source
LMCAKnowledge15.8%source
OTIS Mock AIMEMath62.8%source

API hosts

Live prices and uptime for every host serving Qwen3 30B A3B via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
DeepInfra$0.096$0.40—$0.11—fp8
DeepInfra$0.12$0.50—$0.14100.0%fp8
DeepInfra$0.18$0.75—$0.2199.2%fp8