GPT-5.6 Luna vs Kimi K2.6
42 SHARED BENCHMARKSAcross 42 shared benchmarks, GPT-5.6 Luna scores higher on 31 and Kimi K2.6 on 10, with 1 level. The widest gap is AA-Omniscience · Non-hallucination, where Kimi K2.6 scores 59.5 against 7.4. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $0.95 per million input tokens).
At a glance
Release dates per Artificial Analysis. Prices: Artificial Analysis for GPT-5.6 Luna; Artificial Analysis for Kimi K2.6. ◆ = independently verified score.
Where each leadsby capability area · benchmark wins
Biggest gaps
GPT-5.6 Luna pulls furthest ahead on
- CritPt20.6 vs 8
- FrontierMath Tier 458.5 vs 25.6
- GDPVal47.2 vs 26.3
Kimi K2.6 pulls furthest ahead on
- AA-Omniscience · Non-hallucination59.5 vs 7.4
- LiveBench · Instruction Following64.4 vs 60.1
- CharXiv (RQ)86.7 vs 82.7
Every shared benchmark42 · grouped by area
Reasoning 4
Coding 7
Agentic 7
Factuality 3
Instruction Following 1
Long Context 1
Math 5
Multimodal 3
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.