SShogo Bench

Qwen3.8 Max 0902

2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding

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
55
14% measured
Long-horizon autonomy
59
estimated
Knowledge-work agents
40
estimated
Computer use
38
estimated
Security & context learning
50
estimated

Price

Input
$2.00/M
Output
$6.00/M
Cache read
$0.25/M
3:1 blend
$3.00/M
Agent-effective
$0.77/M

Cheapest host for agents: Alibaba at $0.77/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 79
Terminal-Bench 2.0est.8%predicted 76
DeepSWEest.6%predicted 52
FrontierSWE17.8%5%proximus · $51.27/task
CursorBenchest.4%predicted 39
GSO-Benchest.4%predicted 33
METR Time Horizonsest.10%predicted 76
Vending-Bench 2est.6%predicted 53
PostTrainBenchest.4%predicted 26
APEX-Agentsest.8%predicted 48
GDPvalest.7%predicted 49
Remote Labor Indexest.5%predicted 5
DeepResearch Benchest.5%predicted 48
OSWorld 2.0est.6%predicted 11
OSWorldest.4%predicted 79
Cybenchest.5%predicted 77
CL-benchest.5%predicted 22

Other benchmarks

BenchmarkCategoryScoreSource
Chess PuzzlesReasoning37.0%source
CritPtReasoning17.7%source
FrontierMath Tiers 1-3Math65.6%source
FrontierMath Tier 4Math34.1%source
GPQA DiamondReasoning92.3%source
MirrorCodeCoding47.8%source
OTIS Mock AIMEMath100.0%source
SciCodeCoding52.1%source
SimpleQA VerifiedKnowledge47.3%source

API hosts

Live prices and uptime for every host serving Qwen3.8 Max 0902 via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Alibaba$2.00$6.00$0.25$0.7799.0%—
Alibaba$2.00$6.00$0.25$0.7798.7%—