SShogo Bench

Claude Fable 5 vs Muse Wonder

Claude Fable 5 leads Muse Wonder by 3.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 11 and Muse Wonder wins 2 of 13 shared benchmarks. Muse Wonder is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Muse Wonder
Agentic coding7468
Long-horizon autonomy6970
Knowledge-work agents5250
Computer use5550
Security & context learning5957

Shared benchmarks

BenchmarkClaude Fable 5Muse Wonder
APEX-Agentsindex63.6%66.1%
Vending-Bench 2index$5,680$9,432
PostTrainBenchindex37.3%24.2%
CritPt28.6%28.3%
DTBench98.4%95.2%
FrontierMath Tier 490.2%70.7%
FrontierMath Tiers 1-387.0%82.1%
LMCA61.2%56.8%
MirrorCode70.0%45.6%
OTIS Mock AIME100.0%99.4%
ProofBench95.0%84.0%
SciCode61.0%60.3%
WeirdML v315.6%15.1%

Specs and price

Claude Fable 5Muse Wonder
Agent Index64.1 (#12)60.9 (#15)
Agent $/M$4.62$1.69
Input / output $/M$10.00 / $50.00$4.00 / $20.00
Context1M1M
ReleasedJun 9, 2026Oct 12, 2026
WeightsClosedClosed
API hosts42

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Muse Wonder side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo