SShogo Bench

Claude Sonnet 5 vs GPT-5.4

Claude Sonnet 5 leads GPT-5.4 by 0.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5 wins 7 and GPT-5.4 wins 10 of 17 shared benchmarks. Claude Sonnet 5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5GPT-5.4
Agentic coding5757
Long-horizon autonomy6561
Knowledge-work agents4340
Computer use4042
Security & context learning5154

Shared benchmarks

BenchmarkClaude Sonnet 5GPT-5.4
APEX-Agentsindex54.5%52.4%
DeepSWEindex53.8%51.8%
Vending-Bench 2index$6,378$6,144
GSO-Benchindex37.3%31.4%
Chess Puzzles45.0%48.0%
CritPt16.9%23.4%
DTBench92.5%94.4%
FrontierMath Tier 429.3%49.0%
FrontierMath Tiers 1-365.6%78.6%
GPQA Diamond90.5%93.3%
LMCA50.0%52.0%
MirrorCode63.3%23.3%
OTIS Mock AIME94.7%97.8%
ProofBench77.0%56.0%
SciCode54.3%56.6%
SimpleQA Verified33.7%45.1%
WebDev Arena15371463

Specs and price

Claude Sonnet 5GPT-5.4
Agent Index52.4 (#32)51.6 (#33)
Agent $/M$0.92$1.27
Input / output $/M$2.00 / $10.00$2.50 / $15.00
Context1M1.1M
ReleasedJun 30, 2026Mar 5, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Claude Sonnet 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