SShogo Bench

Claude Fable 5.2 vs Muse Spark 1.1

Claude Fable 5.2 leads Muse Spark 1.1 by 28.1 points on the Shogo Agent Index. Claude Fable 5.2 wins 9 and Muse Spark 1.1 wins 0 of 9 shared benchmarks. Muse Spark 1.1 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Muse Spark 1.1
Agentic coding8653
Long-horizon autonomy7864
Knowledge-work agents6734
Computer use7736
Security & context learning6548

Shared benchmarks

BenchmarkClaude Fable 5.2Muse Spark 1.1
APEX-Agentsindex80.1%31.8%
Vending-Bench 2index$9,628$6,520
Chess Puzzles79.0%34.0%
CritPt35.7%15.1%
DTBench99.2%94.4%
LMCA70.6%49.9%
ProofBench100.0%39.0%
SciCode67.7%58.8%
SimpleQA Verified94.0%57.8%

Specs and price

Claude Fable 5.2Muse Spark 1.1
Agent Index76.4 (#1)48.3 (#40)
Agent $/M$3.21$0.50
Input / output $/M$8.00 / $40.00$1.25 / $4.25
Context1M1M
ReleasedNov 9, 2026Apr 8, 2026
WeightsClosedClosed
API hosts41

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 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