SShogo Bench

Qwen3.5 9B

Qwen instruction model for multilingual chat, reasoning, and tool use

Shogo Agent Index

Unranked

Not ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.

Agentic coding
21
23% measured
Long-horizon autonomy
32
estimated
Knowledge-work agents
20
estimated
Computer use
11
estimated
Security & context learning
22
estimated

Price

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

Cheapest host for agents: Darkbloom at $0.050/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 57
Terminal-Bench 2.09.2%8%little-coder
DeepSWEest.6%predicted 15
FrontierSWEest.5%predicted 2
CursorBenchest.4%predicted 21
GSO-Benchest.4%predicted 4
METR Time Horizonsest.10%predicted 56
Vending-Bench 2est.6%predicted 5
PostTrainBenchest.4%predicted 13
APEX-Agentsest.8%predicted 16
GDPvalest.7%predicted 22
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 43
OSWorld 2.0est.6%predicted 1
OSWorldest.4%predicted 26
Cybenchest.5%predicted 30
CL-benchest.5%predicted 14

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning0.6%source
DTBenchKnowledge71.2%source
GPQA DiamondReasoning79.0%source
LMCAKnowledge24.5%source
OTIS Mock AIMEMath61.7%source
SciCodeCoding29.5%source

API hosts

Live prices and uptime for every host serving Qwen3.5 9B via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Darkbloom$0.080$0.13$0.040$0.050100.0%fp4
DeepInfra$0.080$0.12—$0.080100.0%bf16
DeepInfra$0.10$0.15—$0.1099.3%bf16
SiliconFlow$0.10$0.15—$0.1099.4%fp8
Parasail$0.10$0.25—$0.11100.0%bf16
DeepInfra$0.15$0.23—$0.1598.9%bf16
PrimeIntellect$0.17$0.25$0.15$0.16100.0%bf16
Together$0.17$0.25—$0.1799.6%—