SShogo Bench

Claude Fable 5.2 vs Claude Sonnet 5.5

Claude Fable 5.2 leads Claude Sonnet 5.5 by 7.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.2 wins 16 and Claude Sonnet 5.5 wins 2 of 19 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Claude Sonnet 5.5
Agentic coding8679
Long-horizon autonomy7875
Knowledge-work agents6757
Computer use7761
Security & context learning6561

Shared benchmarks

BenchmarkClaude Fable 5.2Claude Sonnet 5.5
APEX-Agentsindex80.1%75.5%
Vending-Bench 2index$9,628$11,165
FrontierSWEindex69.9%61.9%
CursorBenchindex60.0%55.5%
ARC-AGI98.5%96.5%
ARC-AGI-293.8%83.9%
Chess Puzzles79.0%59.0%
CritPt35.7%31.4%
DTBench99.2%97.3%
FrontierMath Tier 4100.0%80.5%
FrontierMath Tiers 1-395.1%88.8%
GPQA Diamond96.0%95.6%
LMCA70.6%68.3%
OTIS Mock AIME99.7%100.0%
ProofBench100.0%100.0%
SciCode67.7%61.0%
SimpleBench94.9%75.9%
SimpleQA Verified94.0%46.5%
WeirdML v343.1%19.9%

Specs and price

Claude Fable 5.2Claude Sonnet 5.5
Agent Index76.4 (#1)69 (#9)
Agent $/M$3.21$0.84
Input / output $/M$8.00 / $40.00$2.00 / $10.00
Context1M1M
ReleasedNov 9, 2026Sep 28, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 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