VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

Kimi K3 vs MiMo V2.5 Pro

32 SHARED BENCHMARKS

Across 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).

MOONSHOTVSXIAOMI32 SHARED320 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerMoonshotXiaomi
Released
Price per 1M tokens input / output$2.98 / $14.91$0.43 / $0.87
Cost of 1M in + 1M out$17.89$1.30 13.8× less
Head-to-head of 32 shared benchmarks32 wins0 wins
Scores tracked independently verified131 26101 4

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

AreaKimi K3WINSMiMo V2.5 Pro
Reasoning30Kimi K3 leads 3 of 3 · widest: Humanity's Last Exam 46.9 vs 14.8
Coding30Kimi K3 leads 3 of 3 · widest: Terminal-Bench 2.1 85 vs 65.2
Agentic50Kimi K3 leads 5 of 5 · widest: τ-Bench V3 · Banking 46 vs 9.9
Factuality30Kimi K3 leads 3 of 3 · widest: AA-Omniscience · Non-hallucination 46.8 vs 10.8
Long Context10Kimi K3 leads 1 of 1 · widest: AA-LCR 88.7 vs 41.7
Math20Kimi K3 leads 2 of 2 · widest: HMMT Feb. 2026 97 vs 82.6
Multimodal20Kimi K3 leads 2 of 2 · widest: CharXiv (RQ) 91.3 vs 81

Biggest gaps

Kimi K3 pulls furthest ahead on

  1. τ-Bench V3 · Banking46 vs 9.9
  2. AA-Omniscience · Non-hallucination46.8 vs 10.8
  3. 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

BenchmarkKimi K3MARGINMiMo V2.5 Pro
LMArena · WebDev1658 1437
SciCode59.550.6

Agentic 5

BenchmarkKimi K3MARGINMiMo V2.5 Pro
GDPVal51.230.4
Terminal-Bench 4.012.60

Long Context 1

BenchmarkKimi K3MARGINMiMo V2.5 Pro
AA-LCR88.741.7

Math 2

BenchmarkKimi K3MARGINMiMo V2.5 Pro
AIME 202696.7 93.6
HMMT Feb. 202697 82.6

Multimodal 2

BenchmarkKimi K3MARGINMiMo V2.5 Pro
MMMU-Pro80.577.9

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.

Compare Kimi K3 withALL PAIRINGS →

Compare MiMo V2.5 Pro withALL PAIRINGS →