DeepSeek-V4-Flash vs GPT-5.6 Luna
45 SHARED BENCHMARKSAcross 45 shared benchmarks, DeepSeek-V4-Flash scores higher on 10 and GPT-5.6 Luna on 35. The widest gap is FrontierMath Tier 4, where GPT-5.6 Luna scores 58.5 against 24.4. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $0.44 per million input tokens).
At a glance
Release dates per Artificial Analysis. Prices: Artificial Analysis for DeepSeek-V4-Flash; Artificial Analysis for GPT-5.6 Luna. ◆ = independently verified score.
Where each leadsby capability area · benchmark wins
Biggest gaps
DeepSeek-V4-Flash pulls furthest ahead on
- τ-Bench V3 · Banking39.4 vs 31.1
- LiveBench · Instruction Following65.5 vs 60.1
GPT-5.6 Luna pulls furthest ahead on
- FrontierMath Tier 458.5 vs 24.4
- FrontierMath Tiers 1-3 (v2)82.1 vs 57.5
- AA IT-Bench SRE40.3 vs 31.5
Every shared benchmark45 · grouped by area
Reasoning 6
Coding 7
Agentic 5
Factuality 3
Instruction Following 1
Long Context 1
Math 5
Other shared benchmarks 17
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.