SShogo Bench

GPT-5.6 Luna vs GPT-6 Sol

GPT-6 Sol leads GPT-5.6 Luna by 12.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.6 Luna wins 0 and GPT-6 Sol wins 20 of 20 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.6 LunaGPT-6 Sol
Agentic coding5972
Long-horizon autonomy6176
Knowledge-work agents3948
Computer use4054
Security & context learning5159

Shared benchmarks

BenchmarkGPT-5.6 LunaGPT-6 Sol
APEX-Agentsindex43.0%54.3%
Vending-Bench 2index$4,095$14,428
ARC-AGI88.0%95.5%
ARC-AGI-259.5%89.6%
Chess Puzzles43.0%56.0%
CritPt20.6%30.9%
DTBench89.1%97.3%
FrontierCode39.8%49.3%
FrontierMath Tier 461.0%90.0%
FrontierMath Tiers 1-382.1%89.8%
GPQA Diamond91.6%94.3%
LMCA48.5%59.1%
MirrorCode21.1%48.9%
OTIS Mock AIME98.3%100.0%
ProofBench60.0%83.0%
SciCode53.6%57.6%
SimpleBench46.8%73.1%
SimpleQA Verified41.0%60.7%
WebDev Arena15191689
WeirdML v35.2%19.7%

Specs and price

GPT-5.6 LunaGPT-6 Sol
Agent Index51.4 (#34)63.6 (#13)
Agent $/M$0.10$0.92
Input / output $/M$0.20 / $1.20$2.00 / $10.00
Context1.1M1.1M
ReleasedJul 9, 2026Sep 22, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run GPT-5.6 Luna and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo