SShogo Bench

GPT-6 Sol vs Muse Spark 1.3

GPT-6 Sol leads Muse Spark 1.3 by 8.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6 Sol wins 10 and Muse Spark 1.3 wins 4 of 14 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-6 SolMuse Spark 1.3
Agentic coding7260
Long-horizon autonomy7664
Knowledge-work agents4845
Computer use5443
Security & context learning5953

Shared benchmarks

BenchmarkGPT-6 SolMuse Spark 1.3
APEX-Agentsindex54.3%58.6%
Chess Puzzles56.0%37.0%
CritPt30.9%26.0%
DTBench97.3%96.5%
FrontierMath Tier 490.0%46.3%
FrontierMath Tiers 1-389.8%74.4%
LMCA59.1%53.9%
MirrorCode48.9%54.4%
OTIS Mock AIME100.0%99.2%
ProofBench83.0%58.0%
SciCode57.6%59.7%
SimpleBench73.1%81.8%
WebDev Arena16891652
WeirdML v319.7%6.7%

Specs and price

GPT-6 SolMuse Spark 1.3
Agent Index63.6 (#13)54.7 (#28)
Agent $/M$0.92$0.030
Input / output $/M$2.00 / $10.00$0.10 / $0.20
Context1.1M1M
ReleasedSep 22, 2026Sep 2, 2026
WeightsClosedClosed
API hosts52

Don’t pick one. Route.

Shogo can run GPT-6 Sol 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