SShogo Bench

GPT-5.5 vs GPT-5.6 Luna

GPT-5.5 leads GPT-5.6 Luna by 5.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.5 wins 17 and GPT-5.6 Luna wins 3 of 20 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.5GPT-5.6 Luna
Agentic coding6359
Long-horizon autonomy6761
Knowledge-work agents4639
Computer use4340
Security & context learning5551

Shared benchmarks

BenchmarkGPT-5.5GPT-5.6 Luna
APEX-Agentsindex55.1%43.0%
DeepSWEindex67.0%67.2%
Vending-Bench 2index$7,524$4,095
ARC-AGI95.0%88.0%
ARC-AGI-285.0%59.5%
Chess Puzzles63.0%43.0%
CritPt27.1%20.6%
DTBench96.0%89.1%
FrontierCode43.0%39.8%
FrontierMath Tier 472.5%61.0%
FrontierMath Tiers 1-385.3%82.1%
GPQA Diamond94.0%91.6%
LMCA54.3%48.5%
MirrorCode23.3%21.1%
OTIS Mock AIME100.0%98.3%
ProofBench50.0%60.0%
SciCode56.1%53.6%
SimpleBench69.0%46.8%
SimpleQA Verified63.0%41.0%
WebDev Arena15101519

Specs and price

GPT-5.5GPT-5.6 Luna
Agent Index56.7 (#19)51.4 (#34)
Agent $/M$2.55$0.10
Input / output $/M$5.00 / $30.00$0.20 / $1.20
Context1.1M1.1M
ReleasedApr 23, 2026Jul 9, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run GPT-5.5 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