SShogo Bench

Claude Opus 4.6 vs GPT-5.4

Claude Opus 4.6 leads GPT-5.4 by 1.6 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.6 wins 10 and GPT-5.4 wins 13 of 23 shared benchmarks. GPT-5.4 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.6GPT-5.4
Agentic coding5757
Long-horizon autonomy6761
Knowledge-work agents4140
Computer use3942
Security & context learning5754

Shared benchmarks

BenchmarkClaude Opus 4.6GPT-5.4
METR Time Horizonsindex78.9%74.3%
APEX-Agentsindex46.3%52.4%
SWE-bench Verifiedindex78.7%76.9%
Terminal-Bench 2.0index79.8%81.8%
Vending-Bench 2index$8,018$6,144
CL-benchindex20.7%27.9%
DeepResearch Benchindex55.3%35.1%
GSO-Benchindex41.2%31.4%
AlgoTune1.47×1.85×
ARC-AGI94.0%93.7%
ARC-AGI-269.2%74.0%
Chess Puzzles21.0%48.0%
DTBench91.2%94.4%
FrontierMath Tier 426.8%49.0%
FrontierMath Tiers 1-366.0%78.6%
GPQA Diamond90.5%93.3%
Humanity's Last Exam34.4%36.2%
LMCA55.8%52.0%
MirrorCode33.3%23.3%
OTIS Mock AIME94.4%97.8%
ProofBench50.0%56.0%
SimpleQA Verified47.0%45.1%
WebDev Arena15561463

Specs and price

Claude Opus 4.6GPT-5.4
Agent Index53.2 (#31)51.6 (#33)
Agent $/M$2.31$1.27
Input / output $/M$5.00 / $25.00$2.50 / $15.00
Context1M1.1M
ReleasedFeb 5, 2026Mar 5, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Claude Opus 4.6 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