SShogo Bench

GPT-5.4 vs Muse Spark 1.1

GPT-5.4 leads Muse Spark 1.1 by 3.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.4 wins 5 and Muse Spark 1.1 wins 5 of 11 shared benchmarks. Muse Spark 1.1 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.4Muse Spark 1.1
Agentic coding5753
Long-horizon autonomy6164
Knowledge-work agents4034
Computer use4236
Security & context learning5448

Shared benchmarks

BenchmarkGPT-5.4Muse Spark 1.1
APEX-Agentsindex52.4%31.8%
DeepSWEindex51.8%53.3%
Vending-Bench 2index$6,144$6,520
Chess Puzzles48.0%34.0%
CritPt23.4%15.1%
DTBench94.4%94.4%
LMCA52.0%49.9%
ProofBench56.0%39.0%
SciCode56.6%58.8%
SimpleQA Verified45.1%57.8%
WebDev Arena14631542

Specs and price

GPT-5.4Muse Spark 1.1
Agent Index51.6 (#33)48.3 (#40)
Agent $/M$1.27$0.50
Input / output $/M$2.50 / $15.00$1.25 / $4.25
Context1.1M1M
ReleasedMar 5, 2026Apr 8, 2026
WeightsClosedClosed
API hosts41

Don’t pick one. Route.

Shogo can run GPT-5.4 and Muse Spark 1.1 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo