SShogo Bench

Claude Fable 5 vs Claude Opus 5

Claude Opus 5 leads Claude Fable 5 by 1.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 11 and Claude Opus 5 wins 11 of 23 shared benchmarks. Claude Opus 5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Claude Opus 5
Agentic coding7474
Long-horizon autonomy6974
Knowledge-work agents5252
Computer use5556
Security & context learning5959

Shared benchmarks

BenchmarkClaude Fable 5Claude Opus 5
APEX-Agentsindex63.6%65.8%
DeepSWEindex69.9%73.6%
Vending-Bench 2index$5,680$11,182
FrontierSWEindex47.0%52.0%
PostTrainBenchindex37.3%35.7%
ARC-AGI98.5%97.5%
ARC-AGI-289.2%90.4%
Chess Puzzles47.0%43.0%
CritPt28.6%29.1%
DTBench98.4%97.9%
FrontierCode53.5%53.4%
FrontierMath Tier 490.2%73.2%
FrontierMath Tiers 1-387.0%85.6%
GPQA Diamond93.9%93.9%
LMCA61.2%64.5%
MirrorCode70.0%87.8%
OTIS Mock AIME100.0%98.9%
ProofBench95.0%99.0%
SciCode61.0%56.4%
SimpleBench81.9%80.6%
SimpleQA Verified70.7%59.9%
WebDev Arena16281687
WeirdML v315.6%19.0%

Specs and price

Claude Fable 5Claude Opus 5
Agent Index64.1 (#12)65.4 (#11)
Agent $/M$4.62$2.31
Input / output $/M$10.00 / $50.00$5.00 / $25.00
Context1M1M
ReleasedJun 9, 2026Jul 24, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

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

Try both in Shogo