Noometry

Model comparison

GPT-4.1 mini vs MiniMax-M2.1

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 33.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4.1 mini OpenAI

33.5

Rank #232 Confirmed

MiniMax-M2.1 MiniMax

38.4

Rank #177 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and MiniMax-M2.1 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2.1 leads 35.6 to 23.1.
  • MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 205K.
  • MiniMax-M2.1 has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniMiniMax-M2.1
ProviderOpenAIMiniMax
Noometry Index33.538.4
Released2025-04-142025-12-23
WeightsProprietaryOpen
Context window1.05M205K
Max output33K131K
Input $ / M tokens$0.40$0.30
Output $ / M tokens$1.60$1.20
Results tracked4722

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding MiniMax-M2.1 leads

GPT-4.1 mini: 30.4 (#286), MiniMax-M2.1: 40.1 (#132)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Coding13671421
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
LMArena WebDev—1384
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—
ALE-Bench—623.83

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.0 (#52), MiniMax-M2.1: 27.7 (#91)

BenchmarkGPT-4.1 miniMiniMax-M2.1
Terminal-Bench—36.6%
Berkeley Function Calling Leaderboard50.5%—

Reasoning MiniMax-M2.1 leads

GPT-4.1 mini: 10.9 (#335), MiniMax-M2.1: 15.8 (#301)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Hard Prompts13491410
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
NYT Connections (extended)—11.2%
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Epoch Capabilities Index135.01—

Math MiniMax-M2.1 leads

GPT-4.1 mini: 23.1 (#264), MiniMax-M2.1: 35.6 (#142)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Math13431396
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge MiniMax-M2.1 leads

GPT-4.1 mini: 34.7 (#183), MiniMax-M2.1: 37.7 (#143)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Expert13381432
GPQA Diamond65.8%—
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
Vectara Hallucination Rate—11.8%
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.2 (#77), MiniMax-M2.1: —

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Vision1181—

Multilingual MiniMax-M2.1 leads

GPT-4.1 mini: 45.9 (#161), MiniMax-M2.1: 50.2 (#123)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Non-English13181378
LMArena Chinese13291430
LMArena French13571405
LMArena German13491380
LMArena Japanese12911287
LMArena Korean12981297
LMArena Russian13241386
LMArena Spanish13191396

Instruction Following Too close to call

GPT-4.1 mini: 73.9 (#113), MiniMax-M2.1: 74.0 (#108)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Instruction Following13321399
IFEval90.4%—

Long Context MiniMax-M2.1 leads

GPT-4.1 mini: 31.8 (#270), MiniMax-M2.1: 43.2 (#98)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Longer Query13441416
Fiction.LiveBench44.4%—

Writing & Preference MiniMax-M2.1 leads

GPT-4.1 mini: 48.8 (#193), MiniMax-M2.1: 58.5 (#114)

BenchmarkGPT-4.1 miniMiniMax-M2.1
LMArena Text13411392
LMArena Creative Writing13001362
LMArena Multi-Turn13541396
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 33.5 on the Noometry Index.

Which is cheaper, GPT-4.1 mini or MiniMax-M2.1?

MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

Is GPT-4.1 mini or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 30.4 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 205K.

How many benchmarks do GPT-4.1 mini and MiniMax-M2.1 share?

17 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and MiniMax-M2.1 has 22.

Related comparisons

Go deeper