SShogo Bench

Claude Opus 5.5 vs GPT-5.4

Claude Opus 5.5 leads GPT-5.4 by 19.3 points on the Shogo Agent Index. Claude Opus 5.5 wins 18 and GPT-5.4 wins 0 of 18 shared benchmarks. GPT-5.4 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 5.5GPT-5.4
Agentic coding8157
Long-horizon autonomy7661
Knowledge-work agents5840
Computer use6642
Security & context learning6254

Shared benchmarks

BenchmarkClaude Opus 5.5GPT-5.4
APEX-Agentsindex73.5%52.4%
Vending-Bench 2index$9,235$6,144
PostTrainBenchindex43.8%17.8%
ARC-AGI98.5%93.7%
ARC-AGI-293.3%74.0%
Chess Puzzles67.0%48.0%
CritPt31.7%23.4%
DTBench98.9%94.4%
FrontierMath Tier 495.0%49.0%
FrontierMath Tiers 1-391.2%78.6%
GPQA Diamond94.1%93.3%
LMCA68.2%52.0%
MirrorCode95.6%23.3%
OTIS Mock AIME100.0%97.8%
ProofBench100.0%56.0%
SciCode66.9%56.6%
SimpleQA Verified72.2%45.1%
WebDev Arena18201463

Specs and price

Claude Opus 5.5GPT-5.4
Agent Index70.9 (#3)51.6 (#33)
Agent $/M$1.69$1.27
Input / output $/M$4.00 / $20.00$2.50 / $15.00
Context1M1.1M
ReleasedSep 22, 2026Mar 5, 2026
WeightsClosedClosed
API hosts64

Don’t pick one. Route.

Shogo can run Claude Opus 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