SShogo Bench

Claude Fable 5 vs GPT-5.6 Luna

Claude Fable 5 leads GPT-5.6 Luna by 12.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 21 and GPT-5.6 Luna wins 0 of 21 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5GPT-5.6 Luna
Agentic coding7459
Long-horizon autonomy6961
Knowledge-work agents5239
Computer use5540
Security & context learning5951

Shared benchmarks

BenchmarkClaude Fable 5GPT-5.6 Luna
APEX-Agentsindex63.6%43.0%
DeepSWEindex69.9%67.2%
Vending-Bench 2index$5,680$4,095
ARC-AGI98.5%88.0%
ARC-AGI-289.2%59.5%
Chess Puzzles47.0%43.0%
CritPt28.6%20.6%
DTBench98.4%89.1%
FrontierCode53.5%39.8%
FrontierMath Tier 490.2%61.0%
FrontierMath Tiers 1-387.0%82.1%
GPQA Diamond93.9%91.6%
LMCA61.2%48.5%
MirrorCode70.0%21.1%
OTIS Mock AIME100.0%98.3%
ProofBench95.0%60.0%
SciCode61.0%53.6%
SimpleBench81.9%46.8%
SimpleQA Verified70.7%41.0%
WebDev Arena16281519
WeirdML v315.6%5.2%

Specs and price

Claude Fable 5GPT-5.6 Luna
Agent Index64.1 (#12)51.4 (#34)
Agent $/M$4.62$0.10
Input / output $/M$10.00 / $50.00$0.20 / $1.20
Context1M1.1M
ReleasedJun 9, 2026Jul 9, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5 and GPT-5.6 Luna side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo