SShogo Bench

Claude Fable 5 vs Claude Opus 4.8

Claude Fable 5 leads Claude Opus 4.8 by 7.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 22 and Claude Opus 4.8 wins 2 of 24 shared benchmarks. Claude Opus 4.8 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Claude Opus 4.8
Agentic coding7463
Long-horizon autonomy6966
Knowledge-work agents5243
Computer use5547
Security & context learning5955

Shared benchmarks

BenchmarkClaude Fable 5Claude Opus 4.8
APEX-Agentsindex63.6%48.9%
DeepSWEindex69.9%59.0%
Vending-Bench 2index$5,680$5,787
Remote Labor Indexindex16.1%8.3%
GSO-Benchindex78.4%47.1%
PostTrainBenchindex37.3%31.0%
ARC-AGI98.5%92.5%
ARC-AGI-289.2%72.1%
Chess Puzzles47.0%52.0%
CritPt28.6%20.9%
DTBench98.4%94.9%
FrontierCode53.5%46.5%
FrontierMath Tier 490.2%56.1%
FrontierMath Tiers 1-387.0%80.0%
GeoBench89.0%81.0%
GPQA Diamond93.9%91.0%
LMCA61.2%57.5%
MirrorCode70.0%65.6%
OTIS Mock AIME100.0%98.3%
ProofBench95.0%69.0%
SciCode61.0%53.5%
SimpleBench81.9%64.8%
SimpleQA Verified70.7%53.0%
WebDev Arena16281559

Specs and price

Claude Fable 5Claude Opus 4.8
Agent Index64.1 (#12)56.3 (#20)
Agent $/M$4.62$2.31
Input / output $/M$10.00 / $50.00$5.00 / $25.00
Context1M1M
ReleasedJun 9, 2026May 28, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Claude Opus 4.8 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo