SShogo Bench

Claude Haiku 5.5 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads Claude Haiku 5.5 by 11.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 0 and Claude Sonnet 5.5 wins 22 of 22 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5Claude Sonnet 5.5
Agentic coding6779
Long-horizon autonomy6275
Knowledge-work agents4657
Computer use4761
Security & context learning5561

Shared benchmarks

BenchmarkClaude Haiku 5.5Claude Sonnet 5.5
APEX-Agentsindex56.1%75.5%
Vending-Bench 2index$3,602$11,165
FrontierSWEindex43.8%61.9%
CursorBenchindex48.4%55.5%
ARC-AGI89.0%96.5%
ARC-AGI-261.3%83.9%
Chess Puzzles55.0%59.0%
CritPt22.6%31.4%
DTBench95.0%97.3%
FrontierCode46.4%52.1%
FrontierMath Tier 446.3%80.5%
FrontierMath Tiers 1-375.1%88.8%
GPQA Diamond89.6%95.6%
Humanity's Last Exam30.1%46.1%
LMCA51.1%68.3%
MirrorCode78.9%97.8%
OTIS Mock AIME98.9%100.0%
ProofBench89.0%100.0%
SciCode55.0%61.0%
SimpleBench59.2%75.9%
SimpleQA Verified23.8%46.5%
WeirdML v311.7%19.9%

Specs and price

Claude Haiku 5.5Claude Sonnet 5.5
Agent Index57.5 (#18)69 (#9)
Agent $/M$0.050$0.84
Input / output $/M$0.10 / $0.50$2.00 / $10.00
Context1M1M
ReleasedOct 7, 2026Sep 28, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Haiku 5.5 and Claude Sonnet 5.5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo