SShogo Bench

Gemini 4 Carbon vs GPT-5.6 Luna

Gemini 4 Carbon leads GPT-5.6 Luna by 22.2 points on the Shogo Agent Index. Gemini 4 Carbon wins 14 and GPT-5.6 Luna wins 0 of 14 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 4 CarbonGPT-5.6 Luna
Agentic coding8259
Long-horizon autonomy8061
Knowledge-work agents6339
Computer use6840
Security & context learning6351

Shared benchmarks

BenchmarkGemini 4 CarbonGPT-5.6 Luna
APEX-Agentsindex84.2%43.0%
Vending-Bench 2index$16,484$4,095
CursorBenchindex60.4%35.9%
ARC-AGI98.5%88.0%
ARC-AGI-294.2%59.5%
Chess Puzzles78.0%43.0%
CritPt36.0%20.6%
FrontierMath Tier 495.1%61.0%
FrontierMath Tiers 1-390.5%82.1%
GPQA Diamond96.5%91.6%
OTIS Mock AIME100.0%98.3%
SciCode64.2%53.6%
SimpleBench92.6%46.8%
SimpleQA Verified77.7%41.0%

Specs and price

Gemini 4 CarbonGPT-5.6 Luna
Agent Index73.6 (#2)51.4 (#34)
Agent $/M$0.84$0.10
Input / output $/M$2.00 / $10.00$0.20 / $1.20
Context1M1.1M
ReleasedNov 10, 2026Jul 9, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Gemini 4 Carbon 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