SShogo Bench

Muse Spark 1.3 vs Qwen3.8 Max Preview

Muse Spark 1.3 leads Qwen3.8 Max Preview by 1.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Muse Spark 1.3 wins 6 and Qwen3.8 Max Preview wins 5 of 13 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarMuse Spark 1.3Qwen3.8 Max Preview
Agentic coding6058
Long-horizon autonomy6463
Knowledge-work agents4546
Computer use4341
Security & context learning5352

Shared benchmarks

BenchmarkMuse Spark 1.3Qwen3.8 Max Preview
APEX-Agentsindex58.6%63.3%
FrontierSWEindex25.8%15.8%
Chess Puzzles37.0%46.0%
CritPt26.0%20.0%
DTBench96.5%92.0%
FrontierMath Tier 446.3%46.3%
FrontierMath Tiers 1-374.4%74.7%
LMCA53.9%46.2%
MirrorCode54.4%52.2%
OTIS Mock AIME99.2%99.4%
ProofBench58.0%58.0%
SciCode59.7%53.2%
WebDev Arena16521671

Specs and price

Muse Spark 1.3Qwen3.8 Max Preview
Agent Index54.7 (#28)53.6 (#30)
Agent $/M$0.030Free
Input / output $/M$0.10 / $0.20Free / Free
Context1M1M
ReleasedSep 2, 2026Jul 19, 2026
WeightsClosedClosed
API hosts21

Don’t pick one. Route.

Shogo can run Muse Spark 1.3 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