SShogo Bench

Qwen3 14B

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for…

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

Price

Input
$0.12/M
Output
$0.24/M
Cache read
—/M
3:1 blend
$0.15/M
Agent-effective
$0.13/M

Cheapest host for agents: DeepInfra at $0.10/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 10
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 41
OSWorld 2.0est.6%predicted 1
OSWorldest.4%predicted 18
Cybenchest.5%predicted 22
CL-benchest.5%predicted 13

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning0.0%source
DTBenchKnowledge64.0%source
Fiction.LiveBenchLong context62.5%source
GPQA DiamondReasoning63.8%source
LMCAKnowledge18.2%source
OTIS Mock AIMEMath66.4%source
SciCodeCoding31.6%source

API hosts

Live prices and uptime for every host serving Qwen3 14B via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
DeepInfra$0.096$0.19—$0.10100.0%fp8
NextBit$0.10$0.22—$0.11100.0%int4
DeepInfra$0.12$0.24—$0.1396.8%fp8
DeepInfra$0.18$0.36—$0.1999.5%fp8