SShogo Bench

Claude Fable 5.1 vs GPT-5.5

Claude Fable 5.1 leads GPT-5.5 by 11.5 points on the Shogo Agent Index. Claude Fable 5.1 wins 18 and GPT-5.5 wins 2 of 21 shared benchmarks. GPT-5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.1GPT-5.5
Agentic coding8063
Long-horizon autonomy7167
Knowledge-work agents5546
Computer use6243
Security & context learning6155

Shared benchmarks

BenchmarkClaude Fable 5.1GPT-5.5
APEX-Agentsindex68.6%55.1%
Vending-Bench 2index$5,422$7,524
Remote Labor Indexindex17.9%6.3%
GSO-Benchindex88.2%40.2%
PostTrainBenchindex44.6%23.9%
ARC-AGI97.5%95.0%
ARC-AGI-290.0%85.0%
Chess Puzzles48.0%63.0%
CritPt31.1%27.1%
DTBench97.6%96.0%
FrontierCode50.9%43.0%
FrontierMath Tier 487.8%72.5%
FrontierMath Tiers 1-390.2%85.3%
LMCA65.5%54.3%
MirrorCode93.3%23.3%
OTIS Mock AIME100.0%100.0%
ProofBench100.0%50.0%
SciCode63.1%56.1%
SimpleBench86.6%69.0%
SimpleQA Verified70.8%63.0%
WebDev Arena17581510

Specs and price

Claude Fable 5.1GPT-5.5
Agent Index68.2 (#10)56.7 (#19)
Agent $/M$4.01$2.55
Input / output $/M$10.00 / $50.00$5.00 / $30.00
Context1M1.1M
ReleasedSep 1, 2026Apr 23, 2026
WeightsClosedClosed
API hosts34

Don’t pick one. Route.

Shogo can run Claude Fable 5.1 and GPT-5.5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo