SShogo Bench

GPT-5.5 vs Muse Spark 1.3

GPT-5.5 leads Muse Spark 1.3 by 2.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.5 wins 6 and Muse Spark 1.3 wins 7 of 13 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.5Muse Spark 1.3
Agentic coding6360
Long-horizon autonomy6764
Knowledge-work agents4645
Computer use4343
Security & context learning5553

Shared benchmarks

BenchmarkGPT-5.5Muse Spark 1.3
APEX-Agentsindex55.1%58.6%
Chess Puzzles63.0%37.0%
CritPt27.1%26.0%
DTBench96.0%96.5%
FrontierMath Tier 472.5%46.3%
FrontierMath Tiers 1-385.3%74.4%
LMCA54.3%53.9%
MirrorCode23.3%54.4%
OTIS Mock AIME100.0%99.2%
ProofBench50.0%58.0%
SciCode56.1%59.7%
SimpleBench69.0%81.8%
WebDev Arena15101652

Specs and price

GPT-5.5Muse Spark 1.3
Agent Index56.7 (#19)54.7 (#28)
Agent $/M$2.55$0.030
Input / output $/M$5.00 / $30.00$0.10 / $0.20
Context1.1M1M
ReleasedApr 23, 2026Sep 2, 2026
WeightsClosedClosed
API hosts42

Don’t pick one. Route.

Shogo can run GPT-5.5 and Muse Spark 1.3 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo