SShogo Bench

Claude Fable 5 vs Claude Opus 4.6

Claude Fable 5 leads Claude Opus 4.6 by 10.9 points on the Shogo Agent Index. Claude Fable 5 wins 18 and Claude Opus 4.6 wins 1 of 19 shared benchmarks. Claude Opus 4.6 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Claude Opus 4.6
Agentic coding7457
Long-horizon autonomy6967
Knowledge-work agents5241
Computer use5539
Security & context learning5957

Shared benchmarks

BenchmarkClaude Fable 5Claude Opus 4.6
APEX-Agentsindex63.6%46.3%
Vending-Bench 2index$5,680$8,018
Remote Labor Indexindex16.1%4.2%
GSO-Benchindex78.4%41.2%
ARC-AGI98.5%94.0%
ARC-AGI-289.2%69.2%
Chess Puzzles47.0%21.0%
DTBench98.4%91.2%
FrontierCode53.5%26.6%
FrontierMath Tier 490.2%26.8%
FrontierMath Tiers 1-387.0%66.0%
GPQA Diamond93.9%90.5%
LMCA61.2%55.8%
MirrorCode70.0%33.3%
OTIS Mock AIME100.0%94.4%
ProofBench95.0%50.0%
SimpleBench81.9%67.6%
SimpleQA Verified70.7%47.0%
WebDev Arena16281556

Specs and price

Claude Fable 5Claude Opus 4.6
Agent Index64.1 (#12)53.2 (#31)
Agent $/M$4.62$2.31
Input / output $/M$10.00 / $50.00$5.00 / $25.00
Context1M1M
ReleasedJun 9, 2026Feb 5, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Claude Opus 4.6 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo