SShogo Bench

Claude Fable 5.1 vs GPT-5.4

Claude Fable 5.1 leads GPT-5.4 by 16.6 points on the Shogo Agent Index. Claude Fable 5.1 wins 17 and GPT-5.4 wins 1 of 19 shared benchmarks. GPT-5.4 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.1GPT-5.4
Agentic coding8057
Long-horizon autonomy7161
Knowledge-work agents5540
Computer use6242
Security & context learning6154

Shared benchmarks

BenchmarkClaude Fable 5.1GPT-5.4
APEX-Agentsindex68.6%52.4%
Vending-Bench 2index$5,422$6,144
GSO-Benchindex88.2%31.4%
PostTrainBenchindex44.6%17.8%
ARC-AGI97.5%93.7%
ARC-AGI-290.0%74.0%
Chess Puzzles48.0%48.0%
CritPt31.1%23.4%
DTBench97.6%94.4%
FrontierMath Tier 487.8%49.0%
FrontierMath Tiers 1-390.2%78.6%
Humanity's Last Exam46.5%36.2%
LMCA65.5%52.0%
MirrorCode93.3%23.3%
OTIS Mock AIME100.0%97.8%
ProofBench100.0%56.0%
SciCode63.1%56.6%
SimpleQA Verified70.8%45.1%
WebDev Arena17581463

Specs and price

Claude Fable 5.1GPT-5.4
Agent Index68.2 (#10)51.6 (#33)
Agent $/M$4.01$1.27
Input / output $/M$10.00 / $50.00$2.50 / $15.00
Context1M1.1M
ReleasedSep 1, 2026Mar 5, 2026
WeightsClosedClosed
API hosts34

Don’t pick one. Route.

Shogo can run Claude Fable 5.1 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