VerdictPal
Join

Models / MiniMax

MiniMax-M2.1

MiniMax · Released 2025-12-23

AA Intelligence Index 32.1. Listed on Artificial Analysis with API pricing $0.3/$1.2 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.

#118 of 166 on AA Index · current snapshot
32 AA Index · 12 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite58
ContextUnlisted
Input / 1M$0.30
Output / 1M$1.2
Knowledge cutoffunpublished
Statuslightweight

Family profile

Best published score in each covered benchmark family.

72/100 avg
Knowledge
88
Reasoning
83
Math
83
Coding
81
Agentic
29
Long context
66

6 tested benchmark families

Benchmark placements

Where MiniMax-M2.1 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
MMLU-ProKnowledge#9/ 3988Artificial Analysis2026-09-01
LiveCodeBenchCoding#16/ 3181Artificial Analysis2026-09-01
AIMEMath#28/ 3783Artificial Analysis2026-09-01
IFBenchReasoning#56/ 12770Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#108/ 18023Artificial Analysis2026-09-01
AA-LCRLong context#117/ 17966Artificial Analysis2026-09-01
GPQA DiamondReasoning#118/ 18583Artificial Analysis2026-09-01
SciCodeCoding#120/ 18041Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#132/ 18432Artificial Analysis2026-09-01
Terminal-BenchAgentic#155/ 18429Artificial Analysis2026-09-01
AA output speedPerformance#172/ 185Artificial Analysis2026-09-01
AA time to first tokenPerformance#172/ 185Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where MiniMax-M2.1 shows up, it's highlighted.

KnowledgeMiniMax-M2.1 · 88
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningMiniMax-M2.1 · 83
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
MathMiniMax-M2.1 · 83
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    GPT-5 (high)
    99
CodingMiniMax-M2.1 · 81
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticMiniMax-M2.1 · 29
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextMiniMax-M2.1 · 66
  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 MiniMax-M2.1 in the last 120 days. Older rows live in the full table below.

12 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context66.33%Artificial Analysis2
AA output speedPerformance0 t/sArtificial Analysis2
AA time to first tokenPerformance0.00sArtificial Analysis2
AIMEMath82.67%Artificial Analysis2
Artificial Analysis Intelligence IndexReasoning32.1%Artificial Analysis2
GPQA DiamondReasoning83%Artificial Analysis2
Humanity's Last ExamReasoning23.2%Artificial Analysis2
IFBenchReasoning69.86%Artificial Analysis2
LiveCodeBenchCoding81%Artificial Analysis2
MMLU-ProKnowledge87.5%Artificial Analysis2
SciCodeCoding40.7%Artificial Analysis2
Terminal-BenchAgentic28.79%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.

Knowledge88
Reasoning83
Math83
Coding81
Agentic29
Long context66
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for MiniMax-M2.1. Scores link to the original source; gaps mean no public row exists yet.

12 sourced rows

12 of 37 catalog benchmarks have a sourced row for MiniMax-M2.1.

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources