SShogo Bench

Qwen3.7 Max

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

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
52
23% measured
Long-horizon autonomy
57
estimated
Knowledge-work agents
38
estimated
Computer use
36
estimated
Security & context learning
48
estimated

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 $0.66/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verified77.3%8%source
Terminal-Bench 2.0est.8%predicted 71
DeepSWEest.6%predicted 48
FrontierSWEest.5%predicted 15
CursorBenchest.4%predicted 37
GSO-Benchest.4%predicted 28
METR Time Horizonsest.10%predicted 75
Vending-Bench 2est.6%predicted 47
PostTrainBenchest.4%predicted 25
APEX-Agentsest.8%predicted 44
GDPvalest.7%predicted 47
Remote Labor Indexest.5%predicted 4
DeepResearch Benchest.5%predicted 48
OSWorld 2.0est.6%predicted 9
OSWorldest.4%predicted 75
Cybenchest.5%predicted 74
CL-benchest.5%predicted 22

Other benchmarks

BenchmarkCategoryScoreSource
Chess PuzzlesReasoning27.0%source
CritPtReasoning13.4%source
DTBenchKnowledge92.3%source
FrontierMath Tiers 1-3Math64.6%source
FrontierMath Tier 4Math34.1%source
GPQA DiamondReasoning90.9%source
LMCAKnowledge44.0%source
OTIS Mock AIMEMath95.6%source
ProofBenchMath26.0%source
SciCodeCoding49.5%source
SimpleBenchReasoning70.4%source
SimpleQA VerifiedKnowledge55.8%source
WebDev ArenaCoding1517source

API hosts

Live prices and uptime for every host serving Qwen3.7 Max via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Alibaba$1.48$4.42$0.29$0.66100.0%—