Noometry

Model comparison

GPT-4.1 mini vs MiniMax-M2

MiniMax-M2 is the stronger model overall, scoring 37.4 to 33.6 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4.1 mini scores higher in 3 categories and MiniMax-M2 in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2 leads 37.3 to 24.1.
  • The biggest single-benchmark swing is SWE-bench Verified (bash only): 23.9% for GPT-4.1 mini and 61% for MiniMax-M2.
  • MiniMax-M2 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 has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniMiniMax-M2
ProviderOpenAIMiniMax
Noometry Index33.637.4
Released2025-04-142025-10-27
WeightsProprietaryOpen
Context window1.05M205K
Max output33K131K
Input $ / M tokens$0.40$0.30
Output $ / M tokens$1.60$1.20
Results tracked4721

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

Category by category

Coding MiniMax-M2 leads

GPT-4.1 mini: 30.6 (#293), MiniMax-M2: 39.3 (#159)

BenchmarkGPT-4.1 miniMiniMax-M2
SWE-bench Verified (bash only)23.9%61%
LMArena Coding13671370
Aider Polyglot32.4%—
LMArena WebDev—1297
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.3 (#55), MiniMax-M2: 25.1 (#109)

BenchmarkGPT-4.1 miniMiniMax-M2
Terminal-Bench—30%
Berkeley Function Calling Leaderboard50.5%—
Vending-Bench 2—160.6

Reasoning MiniMax-M2 leads

GPT-4.1 mini: 10.8 (#340), MiniMax-M2: 19.4 (#258)

BenchmarkGPT-4.1 miniMiniMax-M2
Kagi LLM Benchmark48.6%57.8%
LMArena Hard Prompts13491357
ARC-AGI-20%—
NYT Connections (extended)—14.8%
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Epoch Capabilities Index135.01—

Math MiniMax-M2 leads

GPT-4.1 mini: 24.1 (#270), MiniMax-M2: 37.3 (#160)

BenchmarkGPT-4.1 miniMiniMax-M2
LMArena Math13431352
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 leads

GPT-4.1 mini: 34.7 (#194), MiniMax-M2: 37.0 (#163)

BenchmarkGPT-4.1 miniMiniMax-M2
LMArena Expert13381337
GPQA Diamond65.8%—
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), MiniMax-M2: —

BenchmarkGPT-4.1 miniMiniMax-M2
LMArena Vision1181—

Multilingual Too close to call

GPT-4.1 mini: 45.7 (#166), MiniMax-M2: 45.3 (#171)

BenchmarkGPT-4.1 miniMiniMax-M2
LMArena Non-English13181313
LMArena Chinese13291366
LMArena French13581335
LMArena German13511355
LMArena Russian13241331
LMArena Spanish13191326
LMArena Japanese1290—
LMArena Korean1298—

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), MiniMax-M2: 70.2 (#166)

BenchmarkGPT-4.1 miniMiniMax-M2
LMArena Instruction Following13331328
IFEval90.4%—

Long Context MiniMax-M2 leads

GPT-4.1 mini: 31.8 (#275), MiniMax-M2: 40.5 (#153)

BenchmarkGPT-4.1 miniMiniMax-M2
LMArena Longer Query13441331
Fiction.LiveBench44.4%—

Writing & Preference MiniMax-M2 leads

GPT-4.1 mini: 48.6 (#199), MiniMax-M2: 53.0 (#162)

BenchmarkGPT-4.1 miniMiniMax-M2
LMArena Text13401340
LMArena Creative Writing13001286
LMArena Multi-Turn13541361
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 33.6 on the Noometry Index.

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

MiniMax-M2 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 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 30.6 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 share?

17 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and MiniMax-M2 has 21.

Related comparisons

Go deeper