SShogo Bench

Claude Opus 4.7 vs GPT-5.6 Luna

Claude Opus 4.7 leads GPT-5.6 Luna by 3.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.7 wins 11 and GPT-5.6 Luna wins 8 of 19 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.7GPT-5.6 Luna
Agentic coding6059
Long-horizon autonomy6961
Knowledge-work agents4139
Computer use4440
Security & context learning5251

Shared benchmarks

BenchmarkClaude Opus 4.7GPT-5.6 Luna
APEX-Agentsindex49.2%43.0%
Vending-Bench 2index$10,937$4,095
ARC-AGI93.5%88.0%
ARC-AGI-275.8%59.5%
Chess Puzzles41.0%43.0%
CritPt12.0%20.6%
DTBench94.7%89.1%
FrontierCode38.5%39.8%
FrontierMath Tier 431.7%61.0%
FrontierMath Tiers 1-370.2%82.1%
GPQA Diamond90.2%91.6%
LMCA52.2%48.5%
MirrorCode43.3%21.1%
OTIS Mock AIME97.8%98.3%
ProofBench54.0%60.0%
SciCode54.5%53.6%
SimpleBench61.7%46.8%
SimpleQA Verified51.7%41.0%
WebDev Arena15671519

Specs and price

Claude Opus 4.7GPT-5.6 Luna
Agent Index54.6 (#29)51.4 (#34)
Agent $/M$2.31$0.10
Input / output $/M$5.00 / $25.00$0.20 / $1.20
Context1M1.1M
ReleasedApr 16, 2026Jul 9, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Opus 4.7 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