Noometry

Model comparison

GPT-4o mini vs MiniMax-M2.7

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 25.5 on the Noometry Index. GPT-4o mini costs 2.0× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4o mini scores higher in 1 category and MiniMax-M2.7 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M2.7 leads 37.7 to 17.7.
  • The biggest single-benchmark swing is WeirdML: 11.8% for GPT-4o mini and 37% for MiniMax-M2.7.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
  • 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-4o miniMiniMax-M2.7
ProviderOpenAIMiniMax
Noometry Index25.537.7
Released2024-07-182026-03-18
WeightsProprietaryOpen
Context window128K205K
Max output16K131K
Input $ / M tokens$0.15$0.30
Output $ / M tokens$0.60$1.20
Results tracked6030

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

Category by category

Coding MiniMax-M2.7 leads

GPT-4o mini: 22.0 (#335), MiniMax-M2.7: 41.8 (#120)

BenchmarkGPT-4o miniMiniMax-M2.7
WeirdML11.8%37%
LMArena Coding12901454
Aider Polyglot3.6%—
LMArena WebDev—1398
SciCode—47%
BigCodeBench Instruct46.1%—
LiveBench Coding43.1%—
BigCodeBench Complete57.4%—
ALE-Bench—599.25
HumanEval+83.5%—
MBPP+72.2%—

Agentic & Tool Use GPT-4o mini leads

GPT-4o mini: 27.5 (#101), MiniMax-M2.7: 25.1 (#111)

BenchmarkGPT-4o miniMiniMax-M2.7
Terminal-Bench—45.1%
BALROG17.4%—
ExploitBench—13.3%
GBAEval—0%

Reasoning MiniMax-M2.7 leads

GPT-4o mini: 8.7 (#347), MiniMax-M2.7: 19.7 (#253)

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Hard Prompts12671422
Epoch Capabilities Index126.56145.85
ARC-AGI-20%—
SimpleBench10.7%—
Kagi LLM Benchmark28.8%—
NYT Connections (extended)—24.7%
CritPt—0.6%
Chess Puzzles0%—
Thematic Generalization—39.3%
LiveBench Reasoning32.8%—
Mystery Game Puzzles12%—
DTBench54.4%—
LiveBench Data Analysis50%—
LMCA10.4%—
LiveBench41.3%—
PIQA88.7%—

Math MiniMax-M2.7 leads

GPT-4o mini: 10.4 (#314), MiniMax-M2.7: 25.9 (#263)

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Math12671420
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.9%—
ProofBench—3%
Omni-MATH28%—
LiveBench Math36.3%—
MATH Level 552.6%—
GSM8K91.3%—

Knowledge MiniMax-M2.7 leads

GPT-4o mini: 17.7 (#284), MiniMax-M2.7: 37.7 (#152)

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Expert12351444
GPQA Diamond37.7%—
SimpleQA Verified8.3%—
MMLU-Pro60.3%—
Confabulations37.2%—
Vectara Hallucination Rate—12.9%
GPQA (HELM)36.8%—
BoolQ88.7%—
MMLU81.8%—

Multimodal Not comparable

GPT-4o mini: 25.9 (#122), MiniMax-M2.7: —

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Vision1066—
Video-MME64.8%—
GeoBench64%—
VPCT34%—

Multilingual MiniMax-M2.7 leads

GPT-4o mini: 42.0 (#199), MiniMax-M2.7: 50.3 (#123)

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Non-English12661382
LMArena Chinese12651441
LMArena French12971421
LMArena German12721398
LMArena Japanese12161262
LMArena Korean11951313
LMArena Russian12751383
LMArena Spanish12761403

Instruction Following MiniMax-M2.7 leads

GPT-4o mini: 61.9 (#239), MiniMax-M2.7: 74.1 (#103)

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Instruction Following12581405
LiveBench Instruction Following56.8%—
IFEval78.2%—

Long Context MiniMax-M2.7 leads

GPT-4o mini: 39.1 (#186), MiniMax-M2.7: 43.3 (#99)

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Longer Query12891419

Writing & Preference MiniMax-M2.7 leads

GPT-4o mini: 39.5 (#248), MiniMax-M2.7: 58.9 (#112)

BenchmarkGPT-4o miniMiniMax-M2.7
LMArena Text12861405
LMArena Creative Writing12681354
LMArena Multi-Turn12851412
Short-Story Creative Writing67.2%—
EQ-Bench Creative Writing873—
WildBench79.1%—
LiveBench Language28.6%—

Frequently asked questions

Is GPT-4o mini better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 25.5 on the Noometry Index. GPT-4o mini costs 2.0× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.

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

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

Is GPT-4o mini or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 22.0 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-4o mini and MiniMax-M2.7 share?

19 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper