Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Inkling-Small vs MiMo V2.5

29 SHARED BENCHMARKS

Across 29 shared benchmarks, Inkling-Small scores higher on 19 and MiMo V2.5 on 10. The widest gap is CritPt, where Inkling-Small scores 8.3 against 3.7. MiMo V2.5 is the cheaper of the two on tracked API pricing ($0.14 against $0.30 per million input tokens).

THINKING MACHINESVSXIAOMI29 SHARED19–10 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerThinking MachinesXiaomi
Released
Price per 1M tokens input / output$0.30 / $1.20$0.14 / $0.28
Cost of 1M in + 1M out$1.50$0.42 3.6× less
Head-to-head of 29 shared benchmarks19 wins10 wins
Scores tracked independently verified71 18 ◆51 3 ◆

Release dates: the vendor's own announcement for Inkling-Small; Artificial Analysis for MiMo V2.5. Prices: Artificial Analysis for Inkling-Small; Artificial Analysis for MiMo V2.5. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaInkling-SmallWINSMiMo V2.5
Reasoning30Inkling-Small leads 3 of 3 · widest: CritPt 8.3 vs 3.7
Coding23MiMo V2.5 leads 3 of 5 · widest: Terminal-Bench 2.1 55.1 vs 63.7
Agentic30Inkling-Small leads 3 of 3 · widest: τ-Bench V3 · Banking 18.8 vs 8.7
Factuality21Inkling-Small leads 2 of 3 · widest: AA-Omniscience · Accuracy 33.2 vs 16.8
Instruction Following10Inkling-Small leads 1 of 1 · widest: IFBench 82.2 vs 67.1
Long Context10Inkling-Small leads 1 of 1
Math20Inkling-Small leads 2 of 2 · widest: HMMT Feb. 2026 90.2 vs 82.6
Multimodal03MiMo V2.5 leads 3 of 3 · widest: CharXiv (RQ) 77.4 vs 81

Biggest gaps

Inkling-Small pulls furthest ahead on

  1. CritPt8.3 vs 3.7
  2. τ-Bench V3 · Banking18.8 vs 8.7
  3. AA-Omniscience · Accuracy33.2 vs 16.8

MiMo V2.5 pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination68.1 vs 37
  2. Terminal-Bench 2.163.7 vs 55.1
  3. CharXiv (RQ)81 vs 77.4

Every shared benchmark29 · grouped by area

Reasoning 3

Coding 5

Agentic 3

BenchmarkInkling-SmallMARGINMiMo V2.5
GDPVal34.624.3
Terminal-Bench 4.010

Instruction Following 1

BenchmarkInkling-SmallMARGINMiMo V2.5
IFBench82.267.1

Long Context 1

BenchmarkInkling-SmallMARGINMiMo V2.5
AA-LCR75.773

Math 2

BenchmarkInkling-SmallMARGINMiMo V2.5
AIME 202695.593.6

Multimodal 3

BenchmarkInkling-SmallMARGINMiMo V2.5
LMArena · Vision1236 ◆◆ 1247
MMMU-Pro7475.4

Other shared benchmarks 8

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.