GPT-5.6 Luna vs Qwen3.5 397B A17B
34 SHARED BENCHMARKSAcross 34 shared benchmarks, GPT-5.6 Luna scores higher on 32 and Qwen3.5 397B A17B on 2. The widest gap is AA Agentic Index, where GPT-5.6 Luna scores 42.7 against 10.6. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $0.60 per million input tokens).
At a glance
Release dates per Artificial Analysis. Prices: Artificial Analysis for GPT-5.6 Luna; Artificial Analysis for Qwen3.5 397B A17B. ◆ = independently verified score.
Where each leadsby capability area · benchmark wins
Biggest gaps
GPT-5.6 Luna pulls furthest ahead on
- GDPVal47.2 vs 14
- FrontierMath Tiers 1-3 (v2)82.1 vs 31.2
- AA ApexAgents35.8 vs 15.3
Qwen3.5 397B A17B pulls furthest ahead on
- AA-Omniscience · Non-hallucination11.1 vs 7.4
Every shared benchmark34 · grouped by area
Reasoning 3
Coding 5
Agentic 6
Factuality 3
Long Context 1
Math 3
Multimodal 2
Other shared benchmarks 11
Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, direct), otherwise the lowest tracked offer.