SShogo Bench

Qwen3.6 Plus

Earlier Qwen multimodal workhorse for million-token agent and document tasks

Shogo Agent Index

Estimated#59 of 92
38.0range 27.1–48.9 · 19% of weight measured
Agentic coding
36
23% measured
Long-horizon autonomy
57
30% measured
Knowledge-work agents
30
estimated
Computer use
26
estimated
Security & context learning
39
50% measured

Price

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

Cheapest host for agents: Alibaba at $0.40/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verified57.9%8%source
Terminal-Bench 2.0est.8%predicted 49
DeepSWEest.6%predicted 33
FrontierSWEest.5%predicted 7
CursorBenchest.4%predicted 30
GSO-Benchest.4%predicted 14
METR Time Horizonsest.10%predicted 69
Vending-Bench 2$5,1156%source
PostTrainBenchest.4%predicted 20
APEX-Agentsest.8%predicted 31
GDPvalest.7%predicted 36
Remote Labor Indexest.5%predicted 2
DeepResearch Benchest.5%predicted 46
OSWorld 2.0est.6%predicted 4
OSWorldest.4%predicted 58
Cybenchest.5%predicted 58
CL-bench20.3%5%source

Other benchmarks

BenchmarkCategoryScoreSource
Chess PuzzlesReasoning16.0%source
CritPtReasoning2.9%source
DTBenchKnowledge81.9%source
FrontierMath Tiers 1-3Math38.2%source
GPQA DiamondReasoning88.4%source
LMCAKnowledge33.1%source
OTIS Mock AIMEMath93.3%source
SciCodeCoding40.7%source
SimpleQA VerifiedKnowledge44.1%source
WebDev ArenaCoding1461source

API hosts

Live prices and uptime for every host serving Qwen3.6 Plus via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Alibaba$0.33$1.95—$0.40100.0%—