SShogo Bench

Claude Fable 5.1 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads Claude Fable 5.1 by 0.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.1 wins 10 and Claude Sonnet 5.5 wins 10 of 22 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.1Claude Sonnet 5.5
Agentic coding8079
Long-horizon autonomy7175
Knowledge-work agents5557
Computer use6261
Security & context learning6161

Shared benchmarks

BenchmarkClaude Fable 5.1Claude Sonnet 5.5
APEX-Agentsindex68.6%75.5%
Vending-Bench 2index$5,422$11,165
FrontierSWEindex56.3%61.9%
CursorBenchindex51.8%55.5%
ARC-AGI97.5%96.5%
ARC-AGI-290.0%83.9%
Chess Puzzles48.0%59.0%
CritPt31.1%31.4%
DTBench97.6%97.3%
FrontierCode50.9%52.1%
FrontierMath Tier 487.8%80.5%
FrontierMath Tiers 1-390.2%88.8%
Humanity's Last Exam46.5%46.1%
LMCA65.5%68.3%
MirrorCode93.3%97.8%
OTIS Mock AIME100.0%100.0%
ProofBench100.0%100.0%
SciCode63.1%61.0%
SimpleBench86.6%75.9%
SimpleQA Verified70.8%46.5%
WebDev Arena17581786
WeirdML v326.0%19.9%

Specs and price

Claude Fable 5.1Claude Sonnet 5.5
Agent Index68.2 (#10)69 (#9)
Agent $/M$4.01$0.84
Input / output $/M$10.00 / $50.00$2.00 / $10.00
Context1M1M
ReleasedSep 1, 2026Sep 28, 2026
WeightsClosedClosed
API hosts35

Don’t pick one. Route.

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

Try both in Shogo