Noometry

Model comparison

GLM-5.3-Flash vs Magistral Small

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.2 on the Noometry Index.

Last verified . 8 shared benchmarks.

GLM-5.3-Flash Z.ai (Zhipu)

51.8

Rank #41 Confirmed

Magistral Small Mistral AI

30.2

Rank #296 Confirmed

Summary

  • They share 8 benchmarks with published results for both. GLM-5.3-Flash scores higher in 4 categories and Magistral Small in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 6.8.
  • The biggest single-benchmark swing is ARC-AGI-1: 91% for GLM-5.3-Flash and 5% for Magistral Small.
  • GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
  • GLM-5.3-Flash accepts more context: 1M tokens versus 128K.

Side by side

GLM-5.3-FlashMagistral Small
ProviderZ.ai (Zhipu)Mistral AI
Noometry Index51.830.2
Released2026-08-202025-06-10
WeightsOpenOpen
Context window1M128K
Max output131K40K
Input $ / M tokens$0.15$0.50
Output $ / M tokens$0.50$1.50
Results tracked4010

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

Category by category

Coding GLM-5.3-Flash leads

GLM-5.3-Flash: 53.1 (#31), Magistral Small: 38.4 (#176)

BenchmarkGLM-5.3-FlashMagistral Small
SciCode51.6%35.2%
DeepSWE63.4%—
FrontierCode31.8%—
CursorBench36.8%—
LMArena WebDev1609—
FrontierSWE18.1%—
LMArena Coding1508—
ALE-Bench303.55—

Agentic & Tool Use Not comparable

GLM-5.3-Flash: 34.2 (#47), Magistral Small: —

BenchmarkGLM-5.3-FlashMagistral Small
APEX-Agents52.8%—
GDP.pdf14%—

Reasoning GLM-5.3-Flash leads

GLM-5.3-Flash: 48.0 (#42), Magistral Small: 6.8 (#350)

BenchmarkGLM-5.3-FlashMagistral Small
ARC-AGI-265.8%0%
ARC-AGI-191%5%
CritPt15.4%0.3%
Chess Puzzles14%3%
Epoch Capabilities Index151.88133.19
Kagi LLM Benchmark—6.3%
LMArena Hard Prompts1491—
Mystery Game Puzzles8%—
DTBench—61.3%
Surface Evolver Bench52.5%—
Bench to the Future 30.15—

Math GLM-5.3-Flash leads

GLM-5.3-Flash: 53.3 (#47), Magistral Small: 26.2 (#261)

BenchmarkGLM-5.3-FlashMagistral Small
OTIS Mock AIME 2024-202593.9%30%
FrontierMath (Tiers 1-3)55.8%—
FrontierMath Tier 417.1%—
ProofBench21%—
LMArena Math1500—

Knowledge GLM-5.3-Flash leads

GLM-5.3-Flash: 58.4 (#36), Magistral Small: 30.9 (#223)

BenchmarkGLM-5.3-FlashMagistral Small
GPQA Diamond90.2%56.1%
LMArena Expert1513—

Multimodal Not comparable

GLM-5.3-Flash: 42.8 (#27), Magistral Small: —

BenchmarkGLM-5.3-FlashMagistral Small
LMArena Vision1296—

Multilingual Not comparable

GLM-5.3-Flash: 56.0 (#25), Magistral Small: —

BenchmarkGLM-5.3-FlashMagistral Small
LMArena Non-English1462—
LMArena Chinese1527—
LMArena French1496—
LMArena German1470—
LMArena Japanese1429—
LMArena Korean1446—
LMArena Russian1469—
LMArena Spanish1471—

Instruction Following Not comparable

GLM-5.3-Flash: 77.5 (#20), Magistral Small: —

BenchmarkGLM-5.3-FlashMagistral Small
LMArena Instruction Following1478—

Long Context Not comparable

GLM-5.3-Flash: 45.4 (#39), Magistral Small: —

BenchmarkGLM-5.3-FlashMagistral Small
LMArena Longer Query1482—

Writing & Preference Not comparable

GLM-5.3-Flash: 65.3 (#50), Magistral Small: —

BenchmarkGLM-5.3-FlashMagistral Small
LMArena Text1471—
LMArena Creative Writing1442—
LMArena Multi-Turn1467—

Frequently asked questions

Is GLM-5.3-Flash better than Magistral Small?

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.2 on the Noometry Index.

Which is cheaper, GLM-5.3-Flash or Magistral Small?

GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Magistral Small lists at $0.50 and $1.50.

Is GLM-5.3-Flash or Magistral Small better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 38.4 in the Noometry coding category.

Which has the bigger context window?

GLM-5.3-Flash does, with 1M tokens against 128K.

How many benchmarks do GLM-5.3-Flash and Magistral Small share?

8 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Magistral Small has 10.

Related comparisons

Go deeper