Kimi K3 vs MiMo V2.5 Pro
32 SHARED BENCHMARKSAcross 32 shared benchmarks, Kimi K3 scores higher on 32 and MiMo V2.5 Pro on 0. The widest gap is Program Bench, where Kimi K3 scores 77.8 against 12.5. MiMo V2.5 Pro is the cheaper of the two on tracked API pricing ($0.43 against $2.98 per million input tokens).
At a glance
Release dates per Artificial Analysis. Prices: Moonshot's own price page for Kimi K3; Artificial Analysis for MiMo V2.5 Pro. ◆ = independently verified score.
Where each leadsby capability area · benchmark wins
Biggest gaps
Kimi K3 pulls furthest ahead on
- τ-Bench V3 · Banking46 vs 9.9
- AA-Omniscience · Non-hallucination46.8 vs 10.8
- Humanity's Last Exam46.9 vs 14.8
MiMo V2.5 Pro pulls furthest ahead on
No ratified-area lead of 3 points or more.
Every shared benchmark32 · grouped by area
Reasoning 3
Coding 3
Agentic 5
Factuality 3
Long Context 1
Math 2
Multimodal 2
Other shared benchmarks 13
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 (moonshot-official, direct), otherwise the lowest tracked offer.