GPT-5.6 Luna vs Kimi K2.5
33 SHARED BENCHMARKSAcross 33 shared benchmarks, GPT-5.6 Luna scores higher on 29 and Kimi K2.5 on 4. The widest gap is CritPt, where GPT-5.6 Luna scores 20.6 against 3.1. 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 Kimi K2.5. ◆ = independently verified score.
Where each leadsby capability area · benchmark wins
Biggest gaps
GPT-5.6 Luna pulls furthest ahead on
- CritPt20.6 vs 3.1
- ARC-AGI-259.6 vs 11.8
- AA ApexAgents35.8 vs 11.5
Kimi K2.5 pulls furthest ahead on
- AA-Omniscience · Non-hallucination34.3 vs 7.4
- LMArena · Vision1269 vs 1259
Every shared benchmark33 · grouped by area
Reasoning 4
Coding 5
Agentic 5
Factuality 3
Long Context 1
Math 2
Multimodal 3
Other shared benchmarks 10
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.