SShogo Bench

Claude Fable 5.1 vs Claude Sonnet 5

Claude Fable 5.1 leads Claude Sonnet 5 by 15.8 points on the Shogo Agent Index. Claude Fable 5.1 wins 18 and Claude Sonnet 5 wins 1 of 19 shared benchmarks. Claude Sonnet 5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.1Claude Sonnet 5
Agentic coding8057
Long-horizon autonomy7165
Knowledge-work agents5543
Computer use6240
Security & context learning6151

Shared benchmarks

BenchmarkClaude Fable 5.1Claude Sonnet 5
APEX-Agentsindex68.6%54.5%
Vending-Bench 2index$5,422$6,378
CursorBenchindex51.8%34.1%
GSO-Benchindex88.2%37.3%
Chess Puzzles48.0%45.0%
CritPt31.1%16.9%
DTBench97.6%92.5%
FrontierCode50.9%42.7%
FrontierMath Tier 487.8%29.3%
FrontierMath Tiers 1-390.2%65.6%
GeoBench84.0%74.0%
LMCA65.5%50.0%
MirrorCode93.3%63.3%
OTIS Mock AIME100.0%94.7%
ProofBench100.0%77.0%
SciCode63.1%54.3%
SimpleBench86.6%60.6%
SimpleQA Verified70.8%33.7%
WebDev Arena17581537

Specs and price

Claude Fable 5.1Claude Sonnet 5
Agent Index68.2 (#10)52.4 (#32)
Agent $/M$4.01$0.92
Input / output $/M$10.00 / $50.00$2.00 / $10.00
Context1M1M
ReleasedSep 1, 2026Jun 30, 2026
WeightsClosedClosed
API hosts35

Don’t pick one. Route.

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

Try both in Shogo