SShogo Bench

Claude Haiku 5.5 vs Claude Opus 5

Claude Opus 5 leads Claude Haiku 5.5 by 7.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 2 and Claude Opus 5 wins 18 of 21 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5Claude Opus 5
Agentic coding6774
Long-horizon autonomy6274
Knowledge-work agents4652
Computer use4756
Security & context learning5559

Shared benchmarks

BenchmarkClaude Haiku 5.5Claude Opus 5
APEX-Agentsindex56.1%65.8%
Vending-Bench 2index$3,602$11,182
FrontierSWEindex43.8%52.0%
CursorBenchindex48.4%46.6%
ARC-AGI89.0%97.5%
ARC-AGI-261.3%90.4%
Chess Puzzles55.0%43.0%
CritPt22.6%29.1%
DTBench95.0%97.9%
FrontierCode46.4%53.4%
FrontierMath Tier 446.3%73.2%
FrontierMath Tiers 1-375.1%85.6%
GPQA Diamond89.6%93.9%
LMCA51.1%64.5%
MirrorCode78.9%87.8%
OTIS Mock AIME98.9%98.9%
ProofBench89.0%99.0%
SciCode55.0%56.4%
SimpleBench59.2%80.6%
SimpleQA Verified23.8%59.9%
WeirdML v311.7%19.0%

Specs and price

Claude Haiku 5.5Claude Opus 5
Agent Index57.5 (#18)65.4 (#11)
Agent $/M$0.050$2.31
Input / output $/M$0.10 / $0.50$5.00 / $25.00
Context1M1M
ReleasedOct 7, 2026Jul 24, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Haiku 5.5 and Claude Opus 5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo