SShogo Bench

Claude Haiku 5.5 vs Muse Spark 1.1

Claude Haiku 5.5 leads Muse Spark 1.1 by 9.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 6 and Muse Spark 1.1 wins 3 of 9 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5Muse Spark 1.1
Agentic coding6753
Long-horizon autonomy6264
Knowledge-work agents4634
Computer use4736
Security & context learning5548

Shared benchmarks

BenchmarkClaude Haiku 5.5Muse Spark 1.1
APEX-Agentsindex56.1%31.8%
Vending-Bench 2index$3,602$6,520
Chess Puzzles55.0%34.0%
CritPt22.6%15.1%
DTBench95.0%94.4%
LMCA51.1%49.9%
ProofBench89.0%39.0%
SciCode55.0%58.8%
SimpleQA Verified23.8%57.8%

Specs and price

Claude Haiku 5.5Muse Spark 1.1
Agent Index57.5 (#18)48.3 (#40)
Agent $/M$0.050$0.50
Input / output $/M$0.10 / $0.50$1.25 / $4.25
Context1M1M
ReleasedOct 7, 2026Apr 8, 2026
WeightsClosedClosed
API hosts51

Don’t pick one. Route.

Shogo can run Claude Haiku 5.5 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