VerdictPal
Join

Models / Xiaomi

MiMo-V2.5-Pro

Xiaomi · Released 2026-04-22

AA Intelligence Index 42.2. Listed on Artificial Analysis with API pricing $0.435/$0.87 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.

#46 of 168 on AA Index · current snapshot
43 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite56
Context128K
Input / 1M$0.43
Output / 1M$0.87
Knowledge cutoffopen
Output speed37 t/s
TTFT (default API)3.74s
Statussolid

Family profile

Best published score in each covered benchmark family.

70/100 avg
Reasoning
87
Coding
50
Agentic
65
Long context
78

4 tested benchmark families

Benchmark placements

Where MiMo-V2.5-Pro 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
IFBenchReasoning#9/ 12780Artificial Analysis2026-09-01
AA time to first tokenPerformance#23/ 186Artificial Analysis2026-09-01
AA-LCRLong context#24/ 17978Artificial Analysis2026-09-01
SciCodeCoding#43/ 18050Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#50/ 18036Artificial Analysis2026-09-01
Terminal-BenchAgentic#57/ 18465Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#58/ 18743Artificial Analysis2026-09-01
GPQA DiamondReasoning#80/ 18587Artificial Analysis2026-09-01
AA output speedPerformance#83/ 187Artificial Analysis2026-09-01
τ³-Bench BankingAgentic#88/ 10610Artificial Analysis2026-09-01
Family context

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

ReasoningMiMo-V2.5-Pro · 87
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingMiMo-V2.5-Pro · 50
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticMiMo-V2.5-Pro · 65
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextMiMo-V2.5-Pro · 78
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

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

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context77.67%Artificial Analysis5
AA output speedPerformance37 t/sArtificial Analysis5
AA time to first tokenPerformance3.74sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning42.9%Artificial Analysis5
GPQA DiamondReasoning86.6%Artificial Analysis5
Humanity's Last ExamReasoning35.7%Artificial Analysis5
IFBenchReasoning79.86%Artificial Analysis5
SciCodeCoding50.2%Artificial Analysis5
τ³-Bench BankingAgentic9.9%Artificial Analysis5
Terminal-BenchAgentic65.17%Artificial Analysis5
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.

Reasoning87
Coding50
Agentic65
Long context78
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for MiMo-V2.5-Pro. 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-Pro.

Reasoning

Coding

Agentic

Long context

Performance

Sources