SShogo Bench

Claude Fable 5 vs Muse Spark 1.3

Claude Fable 5 leads Muse Spark 1.3 by 9.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 15 and Muse Spark 1.3 wins 1 of 16 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Muse Spark 1.3
Agentic coding7460
Long-horizon autonomy6964
Knowledge-work agents5245
Computer use5543
Security & context learning5953

Shared benchmarks

BenchmarkClaude Fable 5Muse Spark 1.3
APEX-Agentsindex63.6%58.6%
FrontierSWEindex47.0%25.8%
Chess Puzzles47.0%37.0%
CritPt28.6%26.0%
DTBench98.4%96.5%
FrontierMath Tier 490.2%46.3%
FrontierMath Tiers 1-387.0%74.4%
GeoBench89.0%86.0%
LMCA61.2%53.9%
MirrorCode70.0%54.4%
OTIS Mock AIME100.0%99.2%
ProofBench95.0%58.0%
SciCode61.0%59.7%
SimpleBench81.9%81.8%
WebDev Arena16281652
WeirdML v315.6%6.7%

Specs and price

Claude Fable 5Muse Spark 1.3
Agent Index64.1 (#12)54.7 (#28)
Agent $/M$4.62$0.030
Input / output $/M$10.00 / $50.00$0.10 / $0.20
Context1M1M
ReleasedJun 9, 2026Sep 2, 2026
WeightsClosedClosed
API hosts42

Don’t pick one. Route.

Shogo can run Claude Fable 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