SShogo Bench

Claude Fable 5 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads Claude Fable 5 by 4.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 7 and Claude Sonnet 5.5 wins 12 of 21 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Claude Sonnet 5.5
Agentic coding7479
Long-horizon autonomy6975
Knowledge-work agents5257
Computer use5561
Security & context learning5961

Shared benchmarks

BenchmarkClaude Fable 5Claude Sonnet 5.5
APEX-Agentsindex63.6%75.5%
Vending-Bench 2index$5,680$11,165
FrontierSWEindex47.0%61.9%
ARC-AGI98.5%96.5%
ARC-AGI-289.2%83.9%
Chess Puzzles47.0%59.0%
CritPt28.6%31.4%
DTBench98.4%97.3%
FrontierCode53.5%52.1%
FrontierMath Tier 490.2%80.5%
FrontierMath Tiers 1-387.0%88.8%
GPQA Diamond93.9%95.6%
LMCA61.2%68.3%
MirrorCode70.0%97.8%
OTIS Mock AIME100.0%100.0%
ProofBench95.0%100.0%
SciCode61.0%61.0%
SimpleBench81.9%75.9%
SimpleQA Verified70.7%46.5%
WebDev Arena16281786
WeirdML v315.6%19.9%

Specs and price

Claude Fable 5Claude Sonnet 5.5
Agent Index64.1 (#12)69 (#9)
Agent $/M$4.62$0.84
Input / output $/M$10.00 / $50.00$2.00 / $10.00
Context1M1M
ReleasedJun 9, 2026Sep 28, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5 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