SShogo Bench

Claude Opus 5 vs GPT-5.6 Luna

Claude Opus 5 leads GPT-5.6 Luna by 14.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 5 wins 22 and GPT-5.6 Luna wins 0 of 23 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 5GPT-5.6 Luna
Agentic coding7459
Long-horizon autonomy7461
Knowledge-work agents5239
Computer use5640
Security & context learning5951

Shared benchmarks

BenchmarkClaude Opus 5GPT-5.6 Luna
APEX-Agentsindex65.8%43.0%
DeepSWEindex73.6%67.2%
Vending-Bench 2index$11,182$4,095
CursorBenchindex46.6%35.9%
ARC-AGI97.5%88.0%
ARC-AGI-290.4%59.5%
BALROG63.4%45.6%
Chess Puzzles43.0%43.0%
CritPt29.1%20.6%
DTBench97.9%89.1%
FrontierCode53.4%39.8%
FrontierMath Tier 473.2%61.0%
FrontierMath Tiers 1-385.6%82.1%
GPQA Diamond93.9%91.6%
LMCA64.5%48.5%
MirrorCode87.8%21.1%
OTIS Mock AIME98.9%98.3%
ProofBench99.0%60.0%
SciCode56.4%53.6%
SimpleBench80.6%46.8%
SimpleQA Verified59.9%41.0%
WebDev Arena16871519
WeirdML v319.0%5.2%

Specs and price

Claude Opus 5GPT-5.6 Luna
Agent Index65.4 (#11)51.4 (#34)
Agent $/M$2.31$0.10
Input / output $/M$5.00 / $25.00$0.20 / $1.20
Context1M1.1M
ReleasedJul 24, 2026Jul 9, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Claude Opus 5 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