SShogo Bench

Claude Haiku 5.5 vs Muse Spark 1.3

Claude Haiku 5.5 leads Muse Spark 1.3 by 2.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 7 and Muse Spark 1.3 wins 7 of 15 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5Muse Spark 1.3
Agentic coding6760
Long-horizon autonomy6264
Knowledge-work agents4645
Computer use4743
Security & context learning5553

Shared benchmarks

BenchmarkClaude Haiku 5.5Muse Spark 1.3
APEX-Agentsindex56.1%58.6%
FrontierSWEindex43.8%25.8%
CursorBenchindex48.4%41.6%
Chess Puzzles55.0%37.0%
CritPt22.6%26.0%
DTBench95.0%96.5%
FrontierMath Tier 446.3%46.3%
FrontierMath Tiers 1-375.1%74.4%
LMCA51.1%53.9%
MirrorCode78.9%54.4%
OTIS Mock AIME98.9%99.2%
ProofBench89.0%58.0%
SciCode55.0%59.7%
SimpleBench59.2%81.8%
WeirdML v311.7%6.7%

Specs and price

Claude Haiku 5.5Muse Spark 1.3
Agent Index57.5 (#18)54.7 (#28)
Agent $/M$0.050$0.030
Input / output $/M$0.10 / $0.50$0.10 / $0.20
Context1M1M
ReleasedOct 7, 2026Sep 2, 2026
WeightsClosedClosed
API hosts52

Don’t pick one. Route.

Shogo can run Claude Haiku 5.5 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