SShogo Bench

Muse Spark 1.1 vs Qwen3.8 Max Preview

Qwen3.8 Max Preview leads Muse Spark 1.1 by 5.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Muse Spark 1.1 wins 4 and Qwen3.8 Max Preview wins 6 of 10 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarMuse Spark 1.1Qwen3.8 Max Preview
Agentic coding5358
Long-horizon autonomy6463
Knowledge-work agents3446
Computer use3641
Security & context learning4852

Shared benchmarks

BenchmarkMuse Spark 1.1Qwen3.8 Max Preview
APEX-Agentsindex31.8%63.3%
DeepSWEindex53.3%57.5%
Chess Puzzles34.0%46.0%
CritPt15.1%20.0%
DTBench94.4%92.0%
LMCA49.9%46.2%
ProofBench39.0%58.0%
SciCode58.8%53.2%
SimpleQA Verified57.8%45.8%
WebDev Arena15421671

Specs and price

Muse Spark 1.1Qwen3.8 Max Preview
Agent Index48.3 (#40)53.6 (#30)
Agent $/M$0.50Free
Input / output $/M$1.25 / $4.25Free / Free
Context1M1M
ReleasedApr 8, 2026Jul 19, 2026
WeightsClosedClosed
API hosts11

Don’t pick one. Route.

Shogo can run Muse Spark 1.1 and Qwen3.8 Max Preview side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo