VerdictPal
Join

Models / Xiaomi

MiMo-V2.5

Xiaomi · Released 2026-04-22

AA Intelligence Index 37.2. Listed on Artificial Analysis with API pricing $0.14/$0.28 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#119 of 184 on AA Index · current snapshot
22 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite49
Context128K
Input / 1M$0.14
Output / 1M$0.28
Knowledge cutoffopen
Output speed66 t/s
TTFT (default API)3.17s
Statussolid

Family profile

Best published score in each covered benchmark family.

67/100 avg
Reasoning
85
Coding
44
Agentic
64
Long context
73

4 tested benchmark families

Benchmark placements

Where MiMo-V2.5 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
AA time to first tokenPerformance#27/ 190Artificial Analysis2026-09-10
AA output speedPerformance#59/ 190Artificial Analysis2026-09-10
SciCodeCoding#64/ 9444Artificial Analysis2026-09-10
IFBenchReasoning#65/ 12767Artificial Analysis2026-09-10
Terminal-BenchAgentic#66/ 18964Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#100/ 18527Artificial Analysis2026-09-10
τ³-Bench BankingAgentic#100/ 1119Artificial Analysis2026-09-10
AA-LCRLong context#102/ 18273Artificial Analysis2026-09-10
GPQA DiamondReasoning#102/ 19085Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#120/ 18822Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where MiMo-V2.5 shows up, it's highlighted.

ReasoningMiMo-V2.5 · 85
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
CodingMiMo-V2.5 · 44
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticMiMo-V2.5 · 64
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextMiMo-V2.5 · 73
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for MiMo-V2.5 in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context73%Artificial Analysis4
AA output speedPerformance66 t/sArtificial Analysis4
AA time to first tokenPerformance3.17sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning22.3%Artificial Analysis4
GPQA DiamondReasoning84.9%Artificial Analysis4
Humanity's Last ExamReasoning27.2%Artificial Analysis4
IFBenchReasoning67.14%Artificial Analysis4
SciCodeCoding43.9%Artificial Analysis4
τ³-Bench BankingAgentic8.66%Artificial Analysis4
Terminal-BenchAgentic63.67%Artificial Analysis4
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning85
Coding44
Agentic64
Long context73
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for MiMo-V2.5. Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 37 catalog benchmarks have a sourced row for MiMo-V2.5.

Reasoning

Coding

Agentic

Long context

Performance

Sources