VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

MiMo V2.5 Pro vs MiniMax M2.7

36 SHARED BENCHMARKS

Across 36 shared benchmarks, MiMo V2.5 Pro scores higher on 18 and MiniMax M2.7 on 16, with 2 level. The widest gap is AA-Omniscience · Non-hallucination, where MiniMax M2.7 scores 64.4 against 10.8. Tracked API pricing per million tokens: MiMo V2.5 Pro $0.43 in / $0.87 out, MiniMax M2.7 $0.30 in / $1.20 out.

XIAOMIVSMINIMAX36 SHARED1816 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerXiaomiMiniMax
Released
Price per 1M tokens input / output$0.43 / $0.87$0.30 / $1.20
Cost of 1M in + 1M out$1.30 1.2× less$1.50
Head-to-head of 36 shared benchmarks18 wins16 wins
Scores tracked independently verified101 499 5

Release dates per Artificial Analysis. Prices: Artificial Analysis for MiMo V2.5 Pro; Artificial Analysis for MiniMax M2.7. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaMiMo V2.5 ProWINSMiniMax M2.7
Reasoning12MiniMax M2.7 leads 2 of 3 · widest: Humanity's Last Exam 14.8 vs 29.6
Coding43MiMo V2.5 Pro leads 4 of 7 · widest: Terminal-Bench 2.1 65.2 vs 55.4
Agentic21MiMo V2.5 Pro leads 2 of 5 · widest: AA IT-Bench SRE 38.2 vs 26.5
Factuality11Even, 1–1 of 2
Instruction Following01MiniMax M2.7 leads 1 of 1 · widest: IFBench 42.7 vs 75.7
Long Context01MiniMax M2.7 leads 1 of 1 · widest: AA-LCR 41.7 vs 78.3
Math20MiMo V2.5 Pro leads 2 of 2 · widest: HMMT Feb. 2026 82.6 vs 71.2

Biggest gaps

MiMo V2.5 Pro pulls furthest ahead on

  1. AA IT-Bench SRE38.2 vs 26.5
  2. GDPVal30.4 vs 24.9
  3. Terminal-Bench 2.165.2 vs 55.4

MiniMax M2.7 pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination64.4 vs 10.8
  2. AA ApexAgents10.6 vs 2.4
  3. Humanity's Last Exam29.6 vs 14.8

Every shared benchmark36 · grouped by area

Reasoning 3

Agentic 5

GDPVal30.424.9
Terminal-Bench 4.000

Instruction Following 1

IFBench42.775.7

Long Context 1

AA-LCR41.778.3

Math 2

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.

Compare MiMo V2.5 Pro withALL PAIRINGS →

Compare MiniMax M2.7 withALL PAIRINGS →