Noometry

Model comparison

GPT-4.5 vs MiniMax-M2.5

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.2 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

MiniMax-M2.5 MiniMax

38.3

Rank #188 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-4.5 scores higher in 5 categories and MiniMax-M2.5 in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M2.5 leads 39.2 to 32.5.
  • The biggest single-benchmark swing is ARC-AGI-1: 10.3% for GPT-4.5 and 63.7% for MiniMax-M2.5.
  • MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

GPT-4.5MiniMax-M2.5
ProviderOpenAIMiniMax
Noometry Index37.238.3
Released2025-02-272026-02-12
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4233

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

Category by category

Coding MiniMax-M2.5 leads

GPT-4.5: 42.2 (#109), MiniMax-M2.5: 48.1 (#58)

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Coding13961381
SWE-bench Verified (bash only)—75.8%
Aider Polyglot44.9%—
LMArena WebDev—1387
SWE-bench Multilingual—68.3%
WeirdML39.4%—
LiveBench Coding75.2%—
ALE-Bench—618.17

Agentic & Tool Use MiniMax-M2.5 leads

GPT-4.5: 27.9 (#97), MiniMax-M2.5: 30.4 (#77)

BenchmarkGPT-4.5MiniMax-M2.5
Terminal-Bench—42.7%
Cybench17.5%—
Vending-Bench 2—-23.16

Reasoning MiniMax-M2.5 leads

GPT-4.5: 13.9 (#330), MiniMax-M2.5: 17.5 (#292)

BenchmarkGPT-4.5MiniMax-M2.5
ARC-AGI-20.8%4.9%
ARC-AGI-110.3%63.7%
LMArena Hard Prompts14031372
Epoch Capabilities Index136.74146.68
SimpleBench34.5%—
Kagi LLM Benchmark—55.2%
NYT Connections (extended)—16.8%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LiveBench Data Analysis64.3%—
ForecastBench61.7—
LiveBench69%—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), MiniMax-M2.5: 26.9 (#253)

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Math14121378
OTIS Mock AIME 2024-202537.8%—
ProofBench—4%
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge MiniMax-M2.5 leads

GPT-4.5: 32.5 (#211), MiniMax-M2.5: 39.2 (#135)

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Expert13941379
GPQA Diamond68.7%—
Humanity's Last Exam5.4%—
Confabulations13.6%—
Vectara Hallucination Rate—9.1%

Multimodal Not comparable

GPT-4.5: 37.6 (#71), MiniMax-M2.5: —

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), MiniMax-M2.5: 47.1 (#152)

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Non-English14131338
LMArena Chinese14211393
LMArena French14181362
LMArena German14571362
LMArena Japanese14161171
LMArena Korean13921232
LMArena Russian14191358
LMArena Spanish—1354

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), MiniMax-M2.5: 71.5 (#148)

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Instruction Following14041353
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), MiniMax-M2.5: 37.5 (#216)

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Longer Query14061366
Fiction.LiveBench63.9%—
CL-bench—11.4%
CL-bench Life—6.3%

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), MiniMax-M2.5: 53.9 (#153)

BenchmarkGPT-4.5MiniMax-M2.5
LMArena Text14171359
LMArena Creative Writing13941331
EQ-Bench Creative Writing12581361
LMArena Multi-Turn14441364
Short-Story Creative Writing75.6%—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than MiniMax-M2.5?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.2 on the Noometry Index.

Is GPT-4.5 or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 42.2 in the Noometry coding category.

How many benchmarks do GPT-4.5 and MiniMax-M2.5 share?

20 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper