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.

#22 of 51 on AA Index · current snapshot
42 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite55
Context128K
Input / 1M$0.43
Output / 1M$0.87
Knowledge cutoffopen
Output speed58 t/s
TTFT (default API)2.38s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
87
Coding
50
Agentic
65
Long context
73

69average across 4 tested 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#6/ 5780Artificial Analysis2026-07-21
AA-LCRLong context#10/ 6473Artificial Analysis2026-07-21
SciCodeCoding#26/ 6550Artificial Analysis2026-07-21
AA time to first tokenPerformance#28/ 69Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#29/ 6534Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#30/ 6742Artificial Analysis2026-07-21
Terminal-BenchAgentic#31/ 6965Artificial Analysis2026-07-21
GPQA DiamondReasoning#39/ 6987Artificial Analysis2026-07-21
AA output speedPerformance#50/ 69Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#59/ 649Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models 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
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
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 · 73
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
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 context73.33%Artificial Analysis2
AA output speedPerformance58 t/sArtificial Analysis2
AA time to first tokenPerformance2.38sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning42.2%Artificial Analysis2
GPQA DiamondReasoning86.6%Artificial Analysis2
Humanity's Last ExamReasoning33.8%Artificial Analysis2
IFBenchReasoning79.86%Artificial Analysis2
SciCodeCoding50.2%Artificial Analysis2
τ³-Bench BankingAgentic8.66%Artificial Analysis2
Terminal-BenchAgentic65.17%Artificial Analysis2
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 context73
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

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 32 catalog benchmarks have a sourced row for MiMo-V2.5-Pro.

Reasoning

Coding

Agentic

Long context

Performance

Sources