SShogo Bench

Claude Sonnet 5.5 vs GPT-5.6 Luna

Claude Sonnet 5.5 leads GPT-5.6 Luna by 17.6 points on the Shogo Agent Index. Claude Sonnet 5.5 wins 21 and GPT-5.6 Luna wins 0 of 21 shared benchmarks. GPT-5.6 Luna is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5GPT-5.6 Luna
Agentic coding7959
Long-horizon autonomy7561
Knowledge-work agents5739
Computer use6140
Security & context learning6151

Shared benchmarks

BenchmarkClaude Sonnet 5.5GPT-5.6 Luna
APEX-Agentsindex75.5%43.0%
Vending-Bench 2index$11,165$4,095
CursorBenchindex55.5%35.9%
ARC-AGI96.5%88.0%
ARC-AGI-283.9%59.5%
Chess Puzzles59.0%43.0%
CritPt31.4%20.6%
DTBench97.3%89.1%
FrontierCode52.1%39.8%
FrontierMath Tier 480.5%61.0%
FrontierMath Tiers 1-388.8%82.1%
GPQA Diamond95.6%91.6%
LMCA68.3%48.5%
MirrorCode97.8%21.1%
OTIS Mock AIME100.0%98.3%
ProofBench100.0%60.0%
SciCode61.0%53.6%
SimpleBench75.9%46.8%
SimpleQA Verified46.5%41.0%
WebDev Arena17861519
WeirdML v319.9%5.2%

Specs and price

Claude Sonnet 5.5GPT-5.6 Luna
Agent Index69 (#9)51.4 (#34)
Agent $/M$0.84$0.10
Input / output $/M$2.00 / $10.00$0.20 / $1.20
Context1M1.1M
ReleasedSep 28, 2026Jul 9, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 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