SShogo Bench

GPT-5.6 Luna vs GPT-6.1 Sol

GPT-6.1 Sol leads GPT-5.6 Luna by 18.6 points on the Shogo Agent Index. GPT-5.6 Luna wins 0 and GPT-6.1 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-6.1 Sol
Agentic coding5980
Long-horizon autonomy6178
Knowledge-work agents3954
Computer use4066
Security & context learning5162

Shared benchmarks

BenchmarkGPT-5.6 LunaGPT-6.1 Sol
APEX-Agentsindex43.0%60.0%
Vending-Bench 2index$4,095$12,861
ARC-AGI88.0%98.5%
ARC-AGI-259.5%94.2%
Chess Puzzles43.0%68.0%
CritPt20.6%31.7%
DTBench89.1%96.5%
FrontierCode39.8%50.2%
FrontierMath Tier 461.0%100.0%
FrontierMath Tiers 1-382.1%93.7%
GPQA Diamond91.6%95.4%
LMCA48.5%62.8%
MirrorCode21.1%61.1%
OTIS Mock AIME98.3%100.0%
ProofBench60.0%99.0%
SciCode53.6%55.8%
SimpleBench46.8%82.9%
SimpleQA Verified41.0%73.9%
WebDev Arena15191759
WeirdML v35.2%38.3%

Specs and price

GPT-5.6 LunaGPT-6.1 Sol
Agent Index51.4 (#34)70 (#5)
Agent $/M$0.10$0.84
Input / output $/M$0.20 / $1.20$2.00 / $10.00
Context1.1M1.1M
ReleasedJul 9, 2026Sep 29, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run GPT-5.6 Luna and GPT-6.1 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo