SShogo Bench

Claude Fable 5.1 vs GPT-6 Astra

GPT-6 Astra leads Claude Fable 5.1 by 2.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.1 wins 9 and GPT-6 Astra wins 14 of 24 shared benchmarks. Claude Fable 5.1 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.1GPT-6 Astra
Agentic coding8080
Long-horizon autonomy7180
Knowledge-work agents5556
Computer use6267
Security & context learning6163

Shared benchmarks

BenchmarkClaude Fable 5.1GPT-6 Astra
APEX-Agentsindex68.6%64.7%
Vending-Bench 2index$5,422$15,515
FrontierSWEindex56.3%65.5%
Remote Labor Indexindex17.9%20.8%
GSO-Benchindex88.2%79.4%
PostTrainBenchindex44.6%41.9%
ARC-AGI97.5%98.5%
ARC-AGI-290.0%95.0%
Chess Puzzles48.0%76.0%
CritPt31.1%31.7%
DTBench97.6%97.3%
FrontierCode50.9%53.3%
FrontierMath Tier 487.8%97.6%
FrontierMath Tiers 1-390.2%93.7%
Humanity's Last Exam46.5%54.8%
LMCA65.5%64.4%
MirrorCode93.3%60.0%
OTIS Mock AIME100.0%100.0%
ProofBench100.0%99.0%
SciCode63.1%56.5%
SimpleBench86.6%86.5%
SimpleQA Verified70.8%75.6%
WebDev Arena17581800
WeirdML v326.0%42.2%

Specs and price

Claude Fable 5.1GPT-6 Astra
Agent Index68.2 (#10)70.9 (#4)
Agent $/M$4.01$4.62
Input / output $/M$10.00 / $50.00$10.00 / $50.00
Context1M1.1M
ReleasedSep 1, 2026Sep 4, 2026
WeightsClosedClosed
API hosts36

Don’t pick one. Route.

Shogo can run Claude Fable 5.1 and GPT-6 Astra side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo