VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

MiMo V2.5 Pro vs Qwen3.7 Plus Preview

36 SHARED BENCHMARKS

Across 36 shared benchmarks, MiMo V2.5 Pro scores higher on 10 and Qwen3.7 Plus Preview on 25, with 1 level. The widest gap is AA ApexAgents, where Qwen3.7 Plus Preview scores 22.4 against 2.4. Tracked API pricing per million tokens: MiMo V2.5 Pro $0.43 in / $0.87 out, Qwen3.7 Plus Preview $0.40 in / $1.60 out.

XIAOMIVSALIBABA36 SHARED1025 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerXiaomiAlibaba
Released
Price per 1M tokens input / output$0.43 / $0.87$0.40 / $1.60
Cost of 1M in + 1M out$1.30 1.5× less$2.00
Head-to-head of 36 shared benchmarks10 wins25 wins
Scores tracked independently verified101 484 4

Release dates per Artificial Analysis. Prices: Artificial Analysis for MiMo V2.5 Pro; Artificial Analysis for Qwen3.7 Plus Preview. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaMiMo V2.5 ProWINSQwen3.7 Plus Preview
Reasoning03Qwen3.7 Plus Preview leads 3 of 3 · widest: CritPt 1.1 vs 9.1
Coding33Even, 3–3 of 6
Agentic13Qwen3.7 Plus Preview leads 3 of 4 · widest: AA ApexAgents 2.4 vs 22.4
Factuality11Even, 1–1 of 2
Instruction Following01Qwen3.7 Plus Preview leads 1 of 1 · widest: IFBench 42.7 vs 78
Long Context01Qwen3.7 Plus Preview leads 1 of 1 · widest: AA-LCR 41.7 vs 73
Math01Qwen3.7 Plus Preview leads 1 of 1 · widest: HMMT Feb. 2026 82.6 vs 92.9
Multimodal04Qwen3.7 Plus Preview leads 4 of 4 · widest: CharXiv (RQ) 81 vs 85.9

Biggest gaps

MiMo V2.5 Pro pulls furthest ahead on

  1. GDPVal30.4 vs 12.8
  2. AA-Omniscience · Accuracy27.2 vs 22.5
  3. SciCode50.6 vs 46.1

Qwen3.7 Plus Preview pulls furthest ahead on

  1. AA ApexAgents22.4 vs 2.4
  2. CritPt9.1 vs 1.1
  3. AA-Omniscience · Non-hallucination72.3 vs 10.8

Every shared benchmark36 · grouped by area

Agentic 4

GDPVal30.412.8
Terminal-Bench 4.001

Instruction Following 1

Long Context 1

Multimodal 4

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 Qwen3.7 Plus Preview withALL PAIRINGS →