Noometry

Model comparison

GPT-4 Turbo vs MiniMax-M2

MiniMax-M2 is the stronger model overall, scoring 37.4 to 30.5 on the Noometry Index.

Last verified . 15 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Summary

  • They share 15 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and MiniMax-M2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2 leads 37.3 to 9.0.
  • MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • MiniMax-M2 accepts more context: 205K tokens versus 128K.
  • MiniMax-M2 has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboMiniMax-M2
ProviderOpenAIMiniMax
Noometry Index30.537.4
Released2023-11-062025-10-27
WeightsProprietaryOpen
Context window128K205K
Max output4K131K
Input $ / M tokens$10$0.30
Output $ / M tokens$30$1.20
Results tracked3621

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

Category by category

Coding MiniMax-M2 leads

GPT-4 Turbo: 33.8 (#249), MiniMax-M2: 39.3 (#159)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Coding12681370
SWE-bench Verified (bash only)—61%
LMArena WebDev—1297
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, MiniMax-M2: 25.1 (#109)

BenchmarkGPT-4 TurboMiniMax-M2
Terminal-Bench—30%
METR Time Horizons36.7%—
Vending-Bench 2—160.6

Reasoning MiniMax-M2 leads

GPT-4 Turbo: 15.3 (#317), MiniMax-M2: 19.4 (#258)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Hard Prompts12511357
SimpleBench25.1%—
Kagi LLM Benchmark—57.8%
NYT Connections (extended)—14.8%
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math MiniMax-M2 leads

GPT-4 Turbo: 9.0 (#322), MiniMax-M2: 37.3 (#160)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Math12721352
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge MiniMax-M2 leads

GPT-4 Turbo: 24.3 (#268), MiniMax-M2: 37.0 (#163)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Expert12231337
GPQA Diamond46.6%—
Confabulations28.4%—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), MiniMax-M2: —

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Vision1090—

Multilingual MiniMax-M2 leads

GPT-4 Turbo: 40.5 (#216), MiniMax-M2: 45.3 (#171)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Non-English12451313
LMArena Chinese12421366
LMArena French12761335
LMArena German12591355
LMArena Russian12591331
LMArena Spanish12601326
LMArena Japanese1194—
LMArena Korean1187—

Instruction Following MiniMax-M2 leads

GPT-4 Turbo: 65.8 (#216), MiniMax-M2: 70.2 (#166)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Instruction Following12491328

Long Context MiniMax-M2 leads

GPT-4 Turbo: 38.0 (#206), MiniMax-M2: 40.5 (#153)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Longer Query12541331

Writing & Preference MiniMax-M2 leads

GPT-4 Turbo: 47.7 (#206), MiniMax-M2: 53.0 (#162)

BenchmarkGPT-4 TurboMiniMax-M2
LMArena Text12721340
LMArena Creative Writing12691286
LMArena Multi-Turn12671361

Frequently asked questions

Is GPT-4 Turbo better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo 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 Turbo lists at $10 and $30.

Is GPT-4 Turbo or MiniMax-M2 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2 does, with 205K tokens against 128K.

How many benchmarks do GPT-4 Turbo and MiniMax-M2 share?

15 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and MiniMax-M2 has 21.

Related comparisons

Go deeper