SShogo Bench

Claude Haiku 5.5 vs GPT-5.4

Claude Haiku 5.5 leads GPT-5.4 by 5.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 6 and GPT-5.4 wins 11 of 17 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5GPT-5.4
Agentic coding6757
Long-horizon autonomy6261
Knowledge-work agents4640
Computer use4742
Security & context learning5554

Shared benchmarks

BenchmarkClaude Haiku 5.5GPT-5.4
APEX-Agentsindex56.1%52.4%
Vending-Bench 2index$3,602$6,144
ARC-AGI89.0%93.7%
ARC-AGI-261.3%74.0%
Chess Puzzles55.0%48.0%
CritPt22.6%23.4%
DTBench95.0%94.4%
FrontierMath Tier 446.3%49.0%
FrontierMath Tiers 1-375.1%78.6%
GPQA Diamond89.6%93.3%
Humanity's Last Exam30.1%36.2%
LMCA51.1%52.0%
MirrorCode78.9%23.3%
OTIS Mock AIME98.9%97.8%
ProofBench89.0%56.0%
SciCode55.0%56.6%
SimpleQA Verified23.8%45.1%

Specs and price

Claude Haiku 5.5GPT-5.4
Agent Index57.5 (#18)51.6 (#33)
Agent $/M$0.050$1.27
Input / output $/M$0.10 / $0.50$2.50 / $15.00
Context1M1.1M
ReleasedOct 7, 2026Mar 5, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Claude Haiku 5.5 and GPT-5.4 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo