Noometry

Model comparison

GLM-5.1 vs Llama 3.1-405B

GLM-5.1 is the stronger model overall, scoring 47.8 to 30.7 on the Noometry Index.

Last verified . 23 shared benchmarks.

GLM-5.1 Z.ai (Zhipu)

47.8

Rank #59 Confirmed

Llama 3.1-405B Meta

30.7

Rank #288 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GLM-5.1 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-5.1 leads 49.7 to 18.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 9.7% for Llama 3.1-405B.

Side by side

GLM-5.1Llama 3.1-405B
ProviderZ.ai (Zhipu)Meta
Noometry Index47.830.7
Released2026-04-072024-07-23
WeightsOpenOpen
Context window200K—
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-5.1 leads

GLM-5.1: 48.7 (#55), Llama 3.1-405B: 33.1 (#262)

BenchmarkGLM-5.1Llama 3.1-405B
WeirdML57.1%21.4%
LMArena Coding14851291
SWE-bench Verified74.2%—
LMArena WebDev1508—
SciCode43.8%—
ALE-Bench887.1—

Agentic & Tool Use GLM-5.1 leads

GLM-5.1: 24.9 (#113), Llama 3.1-405B: 21.0 (#140)

BenchmarkGLM-5.1Llama 3.1-405B
APEX-Agents40.9%—
TheAgentCompany—7.4%
Cybench—7.5%
ExploitBench18.1%—
GBAEval0%—
Vending-Bench 25,634—

Reasoning GLM-5.1 leads

GLM-5.1: 39.1 (#60), Llama 3.1-405B: 16.8 (#300)

BenchmarkGLM-5.1Llama 3.1-405B
SimpleBench55.1%23%
LMArena Hard Prompts14721269
Epoch Capabilities Index149.84128.75
Kagi LLM Benchmark—45%
NYT Connections (extended)77.7%—
CritPt4.6%—
Chess Puzzles19%—
Thematic Generalization69.8%—
DTBench—61.4%
BIG-Bench Hard—82.9%
ForecastBench—59.9
HellaSwag—89.2%
PIQA—85.9%
WinoGrande—89.2%

Math GLM-5.1 leads

GLM-5.1: 49.7 (#60), Llama 3.1-405B: 18.4 (#290)

BenchmarkGLM-5.1Llama 3.1-405B
OTIS Mock AIME 2024-202593.3%9.7%
LMArena Math14731281
FrontierMath (Tiers 1-3)36.8%—
MathArena Final-Answer Competitions67.1%—
ProofBench22.2%—
Omni-MATH—24.9%
MATH Level 5—49.8%
FrontierMath (Feb 2025 set)33.4%—
FrontierMath Tier 4 (v1)12.5%—

Knowledge GLM-5.1 leads

GLM-5.1: 54.9 (#50), Llama 3.1-405B: 30.4 (#227)

BenchmarkGLM-5.1Llama 3.1-405B
GPQA Diamond89.9%50.9%
LMArena Expert14761243
SimpleQA Verified34%—
MMLU-Pro—72.3%
Confabulations—17.6%
GPQA (HELM)—52.2%
ARC (AI2) Challenge—95.3%
MMLU—84.5%
TriviaQA—82.7%

Multilingual GLM-5.1 leads

GLM-5.1: 55.0 (#36), Llama 3.1-405B: 40.7 (#214)

BenchmarkGLM-5.1Llama 3.1-405B
LMArena Non-English14471248
LMArena Chinese15151242
LMArena French14741279
LMArena German14651252
LMArena Japanese14341208
LMArena Korean14181184
LMArena Russian14541265
LMArena Spanish14691260

Instruction Following GLM-5.1 leads

GLM-5.1: 76.3 (#42), Llama 3.1-405B: 65.9 (#214)

BenchmarkGLM-5.1Llama 3.1-405B
LMArena Instruction Following14511259
IFEval—81.1%

Long Context GLM-5.1 leads

GLM-5.1: 44.9 (#53), Llama 3.1-405B: 38.4 (#197)

BenchmarkGLM-5.1Llama 3.1-405B
LMArena Longer Query14661266

Writing & Preference GLM-5.1 leads

GLM-5.1: 66.9 (#31), Llama 3.1-405B: 38.9 (#251)

BenchmarkGLM-5.1Llama 3.1-405B
LMArena Text14611284
LMArena Creative Writing14531262
EQ-Bench Creative Writing1592870
LMArena Multi-Turn14721297
WildBench—78.3%

Frequently asked questions

Is GLM-5.1 better than Llama 3.1-405B?

GLM-5.1 is the stronger model overall, scoring 47.8 to 30.7 on the Noometry Index.

Is GLM-5.1 or Llama 3.1-405B better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 33.1 in the Noometry coding category.

How many benchmarks do GLM-5.1 and Llama 3.1-405B share?

23 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Llama 3.1-405B has 42.

Related comparisons

Go deeper