Noometry

Model comparison

GPT-4 Turbo vs MiniMax-M2.7

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 30.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and MiniMax-M2.7 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2.7 leads 25.9 to 9.0.
  • The biggest single-benchmark swing is WeirdML: 18% for GPT-4 Turbo and 37% for MiniMax-M2.7.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • MiniMax-M2.7 accepts more context: 205K tokens versus 128K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboMiniMax-M2.7
ProviderOpenAIMiniMax
Noometry Index30.537.7
Released2023-11-062026-03-18
WeightsProprietaryOpen
Context window128K205K
Max output4K131K
Input $ / M tokens$10$0.30
Output $ / M tokens$30$1.20
Results tracked3630

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

Category by category

Coding MiniMax-M2.7 leads

GPT-4 Turbo: 33.8 (#249), MiniMax-M2.7: 41.8 (#120)

BenchmarkGPT-4 TurboMiniMax-M2.7
WeirdML18%37%
LMArena Coding12681454
LMArena WebDev—1398
SciCode—47%
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
ALE-Bench—599.25
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, MiniMax-M2.7: 25.1 (#111)

BenchmarkGPT-4 TurboMiniMax-M2.7
Terminal-Bench—45.1%
ExploitBench—13.3%
GBAEval—0%
METR Time Horizons36.7%—

Reasoning MiniMax-M2.7 leads

GPT-4 Turbo: 15.3 (#317), MiniMax-M2.7: 19.7 (#253)

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Hard Prompts12511422
Epoch Capabilities Index127.25145.85
SimpleBench25.1%—
NYT Connections (extended)—24.7%
CritPt—0.6%
Chess Puzzles6%—
Thematic Generalization—39.3%
DTBench61.6%—
LMCA9.8%—
ForecastBench59.4—

Math MiniMax-M2.7 leads

GPT-4 Turbo: 9.0 (#322), MiniMax-M2.7: 25.9 (#263)

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Math12721420
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
ProofBench—3%
MATH Level 546.7%—

Knowledge MiniMax-M2.7 leads

GPT-4 Turbo: 24.3 (#268), MiniMax-M2.7: 37.7 (#152)

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Expert12231444
GPQA Diamond46.6%—
Confabulations28.4%—
Vectara Hallucination Rate—12.9%
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), MiniMax-M2.7: —

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Vision1090—

Multilingual MiniMax-M2.7 leads

GPT-4 Turbo: 40.5 (#216), MiniMax-M2.7: 50.3 (#123)

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Non-English12451382
LMArena Chinese12421441
LMArena French12761421
LMArena German12591398
LMArena Japanese11941262
LMArena Korean11871313
LMArena Russian12591383
LMArena Spanish12601403

Instruction Following MiniMax-M2.7 leads

GPT-4 Turbo: 65.8 (#216), MiniMax-M2.7: 74.1 (#103)

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Instruction Following12491405

Long Context MiniMax-M2.7 leads

GPT-4 Turbo: 38.0 (#206), MiniMax-M2.7: 43.3 (#99)

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Longer Query12541419

Writing & Preference MiniMax-M2.7 leads

GPT-4 Turbo: 47.7 (#206), MiniMax-M2.7: 58.9 (#112)

BenchmarkGPT-4 TurboMiniMax-M2.7
LMArena Text12721405
LMArena Creative Writing12691354
LMArena Multi-Turn12671412

Frequently asked questions

Is GPT-4 Turbo better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or MiniMax-M2.7?

MiniMax-M2.7 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-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 128K.

How many benchmarks do GPT-4 Turbo and MiniMax-M2.7 share?

19 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper