Noometry

Model comparison

GLM-4.5 vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.5 to 41.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

GLM-4.5 Z.ai (Zhipu)

41.4

Rank #125 Confirmed

MiniMax-M3 MiniMax

43.5

Rank #81 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GLM-4.5 scores higher in 0 categories and MiniMax-M3 in 8 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 35.5.
  • MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
  • MiniMax-M3 accepts more context: 1M tokens versus 131K.

Side by side

GLM-4.5MiniMax-M3
ProviderZ.ai (Zhipu)MiniMax
Noometry Index41.443.5
Released2025-07-272026-06-01
WeightsOpenOpen
Context window131K1M
Max output98K512K
Input $ / M tokens$0.60$0.30
Output $ / M tokens$2.20$1.20
Results tracked2741

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

Category by category

Coding Too close to call

GLM-4.5: 41.1 (#121), MiniMax-M3: 41.5 (#111)

BenchmarkGLM-4.5MiniMax-M3
LMArena Coding14341470
ALE-Bench344.82640.02
FrontierCode—14.7%
SWE-bench Verified (bash only)54.2%—
LMArena WebDev—1482
SciCode—47.1%
WeirdML40.6%—
AlgoTune1.52—

Agentic & Tool Use Not comparable

GLM-4.5: —, MiniMax-M3: 22.5 (#121)

BenchmarkGLM-4.5MiniMax-M3
APEX-Agents—37.7%
OSWorld 2.0—4.6%
GBAEval—0.9%
Vending-Bench 2—2,158

Reasoning MiniMax-M3 leads

GLM-4.5: 27.7 (#99), MiniMax-M3: 29.3 (#83)

BenchmarkGLM-4.5MiniMax-M3
LMArena Hard Prompts14301447
SimpleBench—45.8%
Kagi LLM Benchmark57.9%—
NYT Connections (extended)—65.1%
CritPt—3.7%
Chess Puzzles—14%
Mystery Game Puzzles—8%
DTBench—78.9%
LMCA—33.7%
Surface Evolver Bench—55%
Epoch Capabilities Index—147
ForecastBench—61.4

Math MiniMax-M3 leads

GLM-4.5: 36.3 (#119), MiniMax-M3: 39.1 (#83)

BenchmarkGLM-4.5MiniMax-M3
LMArena Math14271432
OTIS Mock AIME 2024-2025—71.1%
ProofBench—18%

Knowledge MiniMax-M3 leads

GLM-4.5: 35.5 (#172), MiniMax-M3: 58.4 (#32)

BenchmarkGLM-4.5MiniMax-M3
LMArena Expert14331462
GPQA Diamond—90.9%
Humanity's Last Exam8.3%—
Confabulations11.3%—

Multimodal Not comparable

GLM-4.5: —, MiniMax-M3: 39.5 (#45)

BenchmarkGLM-4.5MiniMax-M3
LMArena Vision—1254
LMArena Document—1435

Multilingual Too close to call

GLM-4.5: 53.0 (#74), MiniMax-M3: 53.2 (#70)

BenchmarkGLM-4.5MiniMax-M3
LMArena Non-English14171420
LMArena Chinese14651465
LMArena French14231445
LMArena German14061424
LMArena Japanese14161381
LMArena Korean13821372
LMArena Russian14141430
LMArena Spanish14541431

Instruction Following MiniMax-M3 leads

GLM-4.5: 74.3 (#100), MiniMax-M3: 75.7 (#56)

BenchmarkGLM-4.5MiniMax-M3
LMArena Instruction Following14051433

Long Context MiniMax-M3 leads

GLM-4.5: 38.2 (#196), MiniMax-M3: 44.2 (#68)

BenchmarkGLM-4.5MiniMax-M3
LMArena Longer Query14131445
Fiction.LiveBench58.3%—

Writing & Preference MiniMax-M3 leads

GLM-4.5: 57.7 (#121), MiniMax-M3: 62.3 (#79)

BenchmarkGLM-4.5MiniMax-M3
LMArena Text14301433
LMArena Creative Writing13951405
LMArena Multi-Turn14151441
Short-Story Creative Writing73.4%—
EQ-Bench Creative Writing1343—
EQ-Bench 4—1150

Frequently asked questions

Is GLM-4.5 better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 41.4 on the Noometry Index.

Which is cheaper, GLM-4.5 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

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

They score almost the same on coding (41.1 vs 41.5); test both on your own repository before choosing.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 131K.

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

18 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper