SShogo Bench

Claude Fable 5 vs Claude Fable 5.1

Claude Fable 5.1 leads Claude Fable 5 by 4.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 6 and Claude Fable 5.1 wins 17 of 24 shared benchmarks. Claude Fable 5.1 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Claude Fable 5.1
Agentic coding7480
Long-horizon autonomy6971
Knowledge-work agents5255
Computer use5562
Security & context learning5961

Shared benchmarks

BenchmarkClaude Fable 5Claude Fable 5.1
APEX-Agentsindex63.6%68.6%
Vending-Bench 2index$5,680$5,422
FrontierSWEindex47.0%56.3%
Remote Labor Indexindex16.1%17.9%
GSO-Benchindex78.4%88.2%
PostTrainBenchindex37.3%44.6%
ARC-AGI98.5%97.5%
ARC-AGI-289.2%90.0%
Chess Puzzles47.0%48.0%
CritPt28.6%31.1%
DTBench98.4%97.6%
FrontierCode53.5%50.9%
FrontierMath Tier 490.2%87.8%
FrontierMath Tiers 1-387.0%90.2%
GeoBench89.0%84.0%
LMCA61.2%65.5%
MirrorCode70.0%93.3%
OTIS Mock AIME100.0%100.0%
ProofBench95.0%100.0%
SciCode61.0%63.1%
SimpleBench81.9%86.6%
SimpleQA Verified70.7%70.8%
WebDev Arena16281758
WeirdML v315.6%26.0%

Specs and price

Claude Fable 5Claude Fable 5.1
Agent Index64.1 (#12)68.2 (#10)
Agent $/M$4.62$4.01
Input / output $/M$10.00 / $50.00$10.00 / $50.00
Context1M1M
ReleasedJun 9, 2026Sep 1, 2026
WeightsClosedClosed
API hosts43

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Claude Fable 5.1 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo