Noometry

Model comparison

GPT-4.5 vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.5 to 36.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

MiniMax-M3 MiniMax

43.5

Rank #81 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 32.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 71.1% for MiniMax-M3.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

GPT-4.5MiniMax-M3
ProviderOpenAIMiniMax
Noometry Index36.943.5
Released2025-02-272026-06-01
WeightsProprietaryOpen
Context window—1M
Max output—512K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4241

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

Category by category

Coding Too close to call

GPT-4.5: 41.8 (#102), MiniMax-M3: 41.5 (#111)

BenchmarkGPT-4.5MiniMax-M3
LMArena Coding13971470
FrontierCode—14.7%
Aider Polyglot44.9%—
LMArena WebDev—1482
SciCode—47.1%
WeirdML39.4%—
LiveBench Coding75.2%—
ALE-Bench—640.02

Agentic & Tool Use GPT-4.5 leads

GPT-4.5: 27.6 (#92), MiniMax-M3: 22.5 (#121)

BenchmarkGPT-4.5MiniMax-M3
APEX-Agents—37.7%
OSWorld 2.0—4.6%
Cybench17.5%—
GBAEval—0.9%
Vending-Bench 2—2,158

Reasoning MiniMax-M3 leads

GPT-4.5: 14.1 (#320), MiniMax-M3: 29.3 (#83)

BenchmarkGPT-4.5MiniMax-M3
SimpleBench34.5%45.8%
LMArena Hard Prompts14041447
Epoch Capabilities Index136.74147
ForecastBench61.761.4
ARC-AGI-20.8%—
NYT Connections (extended)—65.1%
ARC-AGI-110.3%—
CritPt—3.7%
Chess Puzzles—14%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
Mystery Game Puzzles—8%
DTBench—78.9%
LiveBench Data Analysis64.3%—
LMCA—33.7%
Surface Evolver Bench—55%
LiveBench69%—

Math MiniMax-M3 leads

GPT-4.5: 31.0 (#200), MiniMax-M3: 39.1 (#83)

BenchmarkGPT-4.5MiniMax-M3
OTIS Mock AIME 2024-202537.8%71.1%
LMArena Math14121432
ProofBench—18%
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge MiniMax-M3 leads

GPT-4.5: 32.4 (#205), MiniMax-M3: 58.4 (#32)

BenchmarkGPT-4.5MiniMax-M3
GPQA Diamond68.7%90.9%
LMArena Expert13941462
Humanity's Last Exam5.4%—
Confabulations13.6%—

Multimodal MiniMax-M3 leads

GPT-4.5: 37.0 (#68), MiniMax-M3: 39.5 (#45)

BenchmarkGPT-4.5MiniMax-M3
LMArena Vision11951254
VPCT45%—
LMArena Document—1435

Multilingual Too close to call

GPT-4.5: 52.7 (#78), MiniMax-M3: 53.2 (#70)

BenchmarkGPT-4.5MiniMax-M3
LMArena Non-English14131420
LMArena Chinese14211465
LMArena French14171445
LMArena German14571424
LMArena Japanese14161381
LMArena Korean13921372
LMArena Russian14191430
LMArena Spanish—1431

Instruction Following MiniMax-M3 leads

GPT-4.5: 72.8 (#129), MiniMax-M3: 75.7 (#56)

BenchmarkGPT-4.5MiniMax-M3
LMArena Instruction Following14041433
LiveBench Instruction Following72.3%—

Long Context MiniMax-M3 leads

GPT-4.5: 40.4 (#150), MiniMax-M3: 44.2 (#68)

BenchmarkGPT-4.5MiniMax-M3
LMArena Longer Query14061445
Fiction.LiveBench63.9%—

Writing & Preference MiniMax-M3 leads

GPT-4.5: 57.1 (#129), MiniMax-M3: 62.3 (#79)

BenchmarkGPT-4.5MiniMax-M3
LMArena Text14171433
LMArena Creative Writing13941405
LMArena Multi-Turn14441441
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
EQ-Bench 4—1150
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 36.9 on the Noometry Index.

Is GPT-4.5 or MiniMax-M3 better for coding?

They score almost the same on coding (41.8 vs 41.5); test both on your own repository before choosing.

How many benchmarks do GPT-4.5 and MiniMax-M3 share?

22 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper