SShogo Bench

Claude Fable 5 vs Claude Fable 5.2

Claude Fable 5.2 leads Claude Fable 5 by 12.3 points on the Shogo Agent Index. Claude Fable 5 wins 1 and Claude Fable 5.2 wins 18 of 20 shared benchmarks. Claude Fable 5.2 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Claude Fable 5.2
Agentic coding7486
Long-horizon autonomy6978
Knowledge-work agents5267
Computer use5577
Security & context learning5965

Shared benchmarks

BenchmarkClaude Fable 5Claude Fable 5.2
APEX-Agentsindex63.6%80.1%
Vending-Bench 2index$5,680$9,628
FrontierSWEindex47.0%69.9%
Remote Labor Indexindex16.1%41.3%
PostTrainBenchindex37.3%44.6%
ARC-AGI98.5%98.5%
ARC-AGI-289.2%93.8%
Chess Puzzles47.0%79.0%
CritPt28.6%35.7%
DTBench98.4%99.2%
FrontierMath Tier 490.2%100.0%
FrontierMath Tiers 1-387.0%95.1%
GPQA Diamond93.9%96.0%
LMCA61.2%70.6%
OTIS Mock AIME100.0%99.7%
ProofBench95.0%100.0%
SciCode61.0%67.7%
SimpleBench81.9%94.9%
SimpleQA Verified70.7%94.0%
WeirdML v315.6%43.1%

Specs and price

Claude Fable 5Claude Fable 5.2
Agent Index64.1 (#12)76.4 (#1)
Agent $/M$4.62$3.21
Input / output $/M$10.00 / $50.00$8.00 / $40.00
Context1M1M
ReleasedJun 9, 2026Nov 9, 2026
WeightsClosedClosed
API hosts44

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Claude Fable 5.2 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo