Noometry

Model comparison

GLM-4.5-Air vs Mistral Large 3

GLM-4.5-Air and Mistral Large 3 score almost the same on the Noometry Index (38.9 vs 39.1), so choose on price, context window or the category you care about most.

Last verified . 19 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Mistral Large 3 Mistral AI

39.1

Rank #176 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.5-Air scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-4.5-Air leads 24.1 to 15.2.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 50.9% for Mistral Large 3.
  • Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
  • Mistral Large 3 accepts more context: 262K tokens versus 131K.

Side by side

GLM-4.5-AirMistral Large 3
ProviderZ.ai (Zhipu)Mistral AI
Noometry Index38.939.1
Released2025-07-202025-12-02
WeightsOpenOpen
Context window131K262K
Max output98K8K
Input $ / M tokens$0.20$0.25
Output $ / M tokens$1.10$0.75
Results tracked2724

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

Category by category

Coding Mistral Large 3 leads

GLM-4.5-Air: 33.3 (#259), Mistral Large 3: 34.4 (#237)

BenchmarkGLM-4.5-AirMistral Large 3
LMArena Coding13971448
LMArena WebDev—1230
GSO2.9%—

Reasoning GLM-4.5-Air leads

GLM-4.5-Air: 24.1 (#166), Mistral Large 3: 15.2 (#319)

BenchmarkGLM-4.5-AirMistral Large 3
Kagi LLM Benchmark43%50.9%
LMArena Hard Prompts13791429
NYT Connections (extended)—7.5%
Thematic Generalization—23%
ForecastBench59.2—

Math Mistral Large 3 leads

GLM-4.5-Air: 36.2 (#170), Mistral Large 3: 38.7 (#129)

BenchmarkGLM-4.5-AirMistral Large 3
LMArena Math13961414
Omni-MATH39.1%—

Knowledge Mistral Large 3 leads

GLM-4.5-Air: 35.0 (#191), Mistral Large 3: 36.0 (#177)

BenchmarkGLM-4.5-AirMistral Large 3
Vectara Hallucination Rate9.3%14.5%
LMArena Expert13701421
Humanity's Last Exam8.1%—
MMLU-Pro76.2%—
GPQA (HELM)59.4%—

Multimodal Not comparable

GLM-4.5-Air: —, Mistral Large 3: 38.2 (#66)

BenchmarkGLM-4.5-AirMistral Large 3
LMArena Vision—1221

Multilingual Mistral Large 3 leads

GLM-4.5-Air: 49.1 (#135), Mistral Large 3: 52.5 (#84)

BenchmarkGLM-4.5-AirMistral Large 3
LMArena Non-English13661413
LMArena Chinese14261447
LMArena French13991455
LMArena German13771437
LMArena Japanese13481394
LMArena Korean13081384
LMArena Russian13731411
LMArena Spanish13861440

Instruction Following Mistral Large 3 leads

GLM-4.5-Air: 69.6 (#171), Mistral Large 3: 74.0 (#108)

BenchmarkGLM-4.5-AirMistral Large 3
LMArena Instruction Following13541403
IFEval81.2%—

Long Context Mistral Large 3 leads

GLM-4.5-Air: 41.6 (#135), Mistral Large 3: 43.1 (#105)

BenchmarkGLM-4.5-AirMistral Large 3
LMArena Longer Query13661413

Writing & Preference Mistral Large 3 leads

GLM-4.5-Air: 55.9 (#139), Mistral Large 3: 60.0 (#101)

BenchmarkGLM-4.5-AirMistral Large 3
LMArena Text13841428
LMArena Creative Writing13431386
LMArena Multi-Turn13711429
EQ-Bench Creative Writing—1412
WildBench78.9%—

Frequently asked questions

Is GLM-4.5-Air better than Mistral Large 3?

GLM-4.5-Air and Mistral Large 3 score almost the same on the Noometry Index (38.9 vs 39.1), so choose on price, context window or the category you care about most.

Which is cheaper, GLM-4.5-Air or Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.

Is GLM-4.5-Air or Mistral Large 3 better for coding?

Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 33.3 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 131K.

How many benchmarks do GLM-4.5-Air and Mistral Large 3 share?

19 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Mistral Large 3 has 24.

Related comparisons

Go deeper