SShogo Bench

GPT-5.6 Luna vs GPT-5.6 Sol

GPT-5.6 Sol leads GPT-5.6 Luna by 10.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.6 Luna wins 1 and GPT-5.6 Sol wins 22 of 23 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.6 LunaGPT-5.6 Sol
Agentic coding5971
Long-horizon autonomy6172
Knowledge-work agents3946
Computer use4053
Security & context learning5158

Shared benchmarks

BenchmarkGPT-5.6 LunaGPT-5.6 Sol
APEX-Agentsindex43.0%51.4%
DeepSWEindex67.2%72.7%
Vending-Bench 2index$4,095$9,619
CursorBenchindex35.9%41.7%
ARC-AGI88.0%97.5%
ARC-AGI-259.5%92.5%
BALROG45.6%60.0%
Chess Puzzles43.0%68.0%
CritPt20.6%32.3%
DTBench89.1%96.0%
FrontierCode39.8%47.5%
FrontierMath Tier 461.0%82.9%
FrontierMath Tiers 1-382.1%89.1%
GPQA Diamond91.6%93.5%
LMCA48.5%59.2%
MirrorCode21.1%20.0%
OTIS Mock AIME98.3%100.0%
ProofBench60.0%83.0%
SciCode53.6%57.8%
SimpleBench46.8%71.7%
SimpleQA Verified41.0%69.7%
WebDev Arena15191617
WeirdML v35.2%15.0%

Specs and price

GPT-5.6 LunaGPT-5.6 Sol
Agent Index51.4 (#34)61.8 (#14)
Agent $/M$0.10$1.85
Input / output $/M$0.20 / $1.20$4.00 / $20.00
Context1.1M1.1M
ReleasedJul 9, 2026Aug 7, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

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

Try both in Shogo