Noometry

Model comparison

GLM-5.3 vs Llama 3.1-405B

GLM-5.3 is the stronger model overall, scoring 54.6 to 30.4 on the Noometry Index.

Last verified . 23 shared benchmarks.

GLM-5.3 Z.ai (Zhipu)

54.6

Rank #25 Confirmed

Llama 3.1-405B Meta

30.4

Rank #279 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GLM-5.3 scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.3 leads 62.1 to 17.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 91.1% for GLM-5.3 and 9.7% for Llama 3.1-405B.

Side by side

GLM-5.3Llama 3.1-405B
ProviderZ.ai (Zhipu)Meta
Noometry Index54.630.4
Released2026-08-142024-07-23
WeightsOpenOpen
Context window1M—
Max output131K—
Input $ / M tokens$1.40—
Output $ / M tokens$4.40—
Results tracked4142

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

Category by category

Coding GLM-5.3 leads

GLM-5.3: 59.0 (#12), Llama 3.1-405B: 32.7 (#257)

BenchmarkGLM-5.3Llama 3.1-405B
WeirdML75.4%21.4%
LMArena Coding14991291
DeepSWE69%—
FrontierCode40.1%—
LMArena WebDev1623—
FrontierSWE30.2%—
SciCode59%—
ALE-Bench1,317—

Agentic & Tool Use GLM-5.3 leads

GLM-5.3: 36.3 (#34), Llama 3.1-405B: 20.9 (#131)

BenchmarkGLM-5.3Llama 3.1-405B
APEX-Agents56.6%—
TheAgentCompany—7.4%
Cybench—7.5%
Vending-Bench 28,164—

Reasoning GLM-5.3 leads

GLM-5.3: 45.2 (#42), Llama 3.1-405B: 16.4 (#293)

BenchmarkGLM-5.3Llama 3.1-405B
LMArena Hard Prompts14911270
DTBench87.7%61.4%
Epoch Capabilities Index155.56128.76
SimpleBench—23%
Kagi LLM Benchmark—45%
NYT Connections (extended)74.2%—
CritPt19.1%—
Chess Puzzles21%—
Mystery Game Puzzles33%—
LMCA55.5%—
Bench to the Future 30.15—
BIG-Bench Hard—82.9%
ForecastBench—59.9
HellaSwag—89.2%
PIQA—85.9%
WinoGrande—89.2%

Math GLM-5.3 leads

GLM-5.3: 62.1 (#27), Llama 3.1-405B: 17.3 (#283)

BenchmarkGLM-5.3Llama 3.1-405B
OTIS Mock AIME 2024-202591.1%9.7%
LMArena Math14931281
FrontierMath (Tiers 1-3)68.8%—
FrontierMath Tier 429.3%—
ProofBench49%—
Omni-MATH—24.9%
MATH Level 5—49.8%

Knowledge GLM-5.3 leads

GLM-5.3: 58.3 (#34), Llama 3.1-405B: 30.4 (#221)

BenchmarkGLM-5.3Llama 3.1-405B
GPQA Diamond90.9%50.9%
LMArena Expert15121243
SimpleQA Verified41%—
MMLU-Pro—72.3%
Confabulations—17.6%
GPQA (HELM)—52.2%
ARC (AI2) Challenge—95.3%
MMLU—84.5%
TriviaQA—82.7%

Multilingual GLM-5.3 leads

GLM-5.3: 55.9 (#27), Llama 3.1-405B: 40.9 (#209)

BenchmarkGLM-5.3Llama 3.1-405B
LMArena Non-English14571248
LMArena Chinese15231242
LMArena French14991278
LMArena German15051252
LMArena Japanese14381208
LMArena Korean14781184
LMArena Russian14601265
LMArena Spanish14441259

Instruction Following GLM-5.3 leads

GLM-5.3: 77.8 (#15), Llama 3.1-405B: 66.1 (#209)

BenchmarkGLM-5.3Llama 3.1-405B
LMArena Instruction Following14811259
IFEval—81.1%

Long Context GLM-5.3 leads

GLM-5.3: 45.5 (#32), Llama 3.1-405B: 38.4 (#192)

BenchmarkGLM-5.3Llama 3.1-405B
LMArena Longer Query14851266

Writing & Preference GLM-5.3 leads

GLM-5.3: 75.9 (#6), Llama 3.1-405B: 39.1 (#246)

BenchmarkGLM-5.3Llama 3.1-405B
LMArena Text14731284
LMArena Creative Writing14591262
EQ-Bench Creative Writing2075870
LMArena Multi-Turn14731297
WildBench—78.3%

Frequently asked questions

Is GLM-5.3 better than Llama 3.1-405B?

GLM-5.3 is the stronger model overall, scoring 54.6 to 30.4 on the Noometry Index.

Is GLM-5.3 or Llama 3.1-405B better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.0 versus 32.7 in the Noometry coding category.

How many benchmarks do GLM-5.3 and Llama 3.1-405B share?

23 benchmarks have published results for both models. GLM-5.3 has 41 scored results on Noometry and Llama 3.1-405B has 42.

Related comparisons

Go deeper