SShogo Bench

Claude Fable 5 vs Claude Opus 5.5

Claude Opus 5.5 leads Claude Fable 5 by 6.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 0 and Claude Opus 5.5 wins 21 of 23 shared benchmarks. Claude Opus 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Claude Opus 5.5
Agentic coding7481
Long-horizon autonomy6976
Knowledge-work agents5258
Computer use5566
Security & context learning5962

Shared benchmarks

BenchmarkClaude Fable 5Claude Opus 5.5
APEX-Agentsindex63.6%73.5%
Vending-Bench 2index$5,680$9,235
FrontierSWEindex47.0%62.3%
Remote Labor Indexindex16.1%21.3%
PostTrainBenchindex37.3%43.8%
ARC-AGI98.5%98.5%
ARC-AGI-289.2%93.3%
Chess Puzzles47.0%67.0%
CritPt28.6%31.7%
DTBench98.4%98.9%
FrontierCode53.5%54.6%
FrontierMath Tier 490.2%95.0%
FrontierMath Tiers 1-387.0%91.2%
GPQA Diamond93.9%94.1%
LMCA61.2%68.2%
MirrorCode70.0%95.6%
OTIS Mock AIME100.0%100.0%
ProofBench95.0%100.0%
SciCode61.0%66.9%
SimpleBench81.9%88.4%
SimpleQA Verified70.7%72.2%
WebDev Arena16281820
WeirdML v315.6%31.2%

Specs and price

Claude Fable 5Claude Opus 5.5
Agent Index64.1 (#12)70.9 (#3)
Agent $/M$4.62$1.69
Input / output $/M$10.00 / $50.00$4.00 / $20.00
Context1M1M
ReleasedJun 9, 2026Sep 22, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Claude Opus 5.5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo