SShogo Bench

Qwen3 Max

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

Shogo Agent Index

Estimated#79 of 92
25.7range 16.2–35.3 · 11% of weight measured
Agentic coding
27
estimated
Long-horizon autonomy
33
30% measured
Knowledge-work agents
23
estimated
Computer use
15
estimated
Security & context learning
27
50% measured

Price

Input
$0.36/M
Output
$1.43/M
Cache read
$0.072/M
3:1 blend
$0.63/M
Agent-effective
$0.18/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 62
Terminal-Bench 2.0est.8%predicted 24
DeepSWEest.6%predicted 19
FrontierSWEest.5%predicted 3
CursorBenchest.4%predicted 24
GSO-Benchest.4%predicted 6
METR Time Horizonsest.10%predicted 60
Vending-Bench 2$726%source
PostTrainBenchest.4%predicted 15
APEX-Agentsest.8%predicted 20
GDPvalest.7%predicted 26
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 44
OSWorld 2.0est.6%predicted 2
OSWorldest.4%predicted 35
Cybenchest.5%predicted 39
CL-bench14.5%5%source

Other benchmarks

BenchmarkCategoryScoreSource
DTBenchKnowledge82.1%source
Fiction.LiveBenchLong context66.7%source
FrontierMath Tiers 1-3Math18.9%source
GPQA DiamondReasoning72.6%source
LMCAKnowledge28.3%source
MATH Level 5Math97.1%source
OTIS Mock AIMEMath73.3%source
SimpleQA VerifiedKnowledge48.7%source