Noometry

Model comparison

GLM-4.7 vs Llama 3.1-405B

GLM-4.7 is the stronger model overall, scoring 42.0 to 30.7 on the Noometry Index.

Last verified . 22 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Llama 3.1-405B Meta

30.7

Rank #288 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GLM-4.7 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 writing & preference, where GLM-4.7 leads 60.9 to 38.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 9.7% for Llama 3.1-405B.

Side by side

GLM-4.7Llama 3.1-405B
ProviderZ.ai (Zhipu)Meta
Noometry Index42.030.7
Released2025-12-222024-07-23
WeightsOpenOpen
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked3642

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

Category by category

Coding GLM-4.7 leads

GLM-4.7: 44.0 (#79), Llama 3.1-405B: 33.1 (#262)

BenchmarkGLM-4.7Llama 3.1-405B
LMArena Coding14541291
LMArena WebDev1435—
SciCode45.1%—
WeirdML—21.4%
ALE-Bench399.48—

Agentic & Tool Use GLM-4.7 leads

GLM-4.7: 26.5 (#103), Llama 3.1-405B: 21.0 (#140)

BenchmarkGLM-4.7Llama 3.1-405B
Terminal-Bench33.4%—
TheAgentCompany—7.4%
Cybench—7.5%
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 24.3 (#164), Llama 3.1-405B: 16.8 (#300)

BenchmarkGLM-4.7Llama 3.1-405B
SimpleBench47.7%23%
LMArena Hard Prompts14431269
Epoch Capabilities Index143.51128.75
Kagi LLM Benchmark—45%
CritPt1.7%—
Chess Puzzles6%—
DTBench—61.4%
BIG-Bench Hard—82.9%
ForecastBench—59.9
HellaSwag—89.2%
PIQA—85.9%
WinoGrande—89.2%

Math GLM-4.7 leads

GLM-4.7: 38.6 (#135), Llama 3.1-405B: 18.4 (#290)

BenchmarkGLM-4.7Llama 3.1-405B
OTIS Mock AIME 2024-202583.3%9.7%
LMArena Math14231281
ProofBench6%—
Omni-MATH—24.9%
MATH Level 5—49.8%
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#80), Llama 3.1-405B: 30.4 (#227)

BenchmarkGLM-4.7Llama 3.1-405B
GPQA Diamond83.3%50.9%
LMArena Expert14241243
SimpleQA Verified32.2%—
MMLU-Pro—72.3%
Confabulations—17.6%
Vectara Hallucination Rate11.7%—
GPQA (HELM)—52.2%
ARC (AI2) Challenge—95.3%
MMLU—84.5%
TriviaQA—82.7%

Multilingual GLM-4.7 leads

GLM-4.7: 52.8 (#79), Llama 3.1-405B: 40.7 (#214)

BenchmarkGLM-4.7Llama 3.1-405B
LMArena Non-English14171248
LMArena Chinese14951242
LMArena French14321279
LMArena German14241252
LMArena Japanese14391208
LMArena Korean13991184
LMArena Russian14231265
LMArena Spanish14341260

Instruction Following GLM-4.7 leads

GLM-4.7: 74.4 (#95), Llama 3.1-405B: 65.9 (#214)

BenchmarkGLM-4.7Llama 3.1-405B
LMArena Instruction Following14111259
IFEval—81.1%

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#116), Llama 3.1-405B: 38.4 (#197)

BenchmarkGLM-4.7Llama 3.1-405B
LMArena Longer Query14321266
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 60.9 (#93), Llama 3.1-405B: 38.9 (#251)

BenchmarkGLM-4.7Llama 3.1-405B
LMArena Text14351284
LMArena Creative Writing14011262
EQ-Bench Creative Writing1413870
LMArena Multi-Turn14461297
WildBench—78.3%

Frequently asked questions

Is GLM-4.7 better than Llama 3.1-405B?

GLM-4.7 is the stronger model overall, scoring 42.0 to 30.7 on the Noometry Index.

Is GLM-4.7 or Llama 3.1-405B better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 33.1 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Llama 3.1-405B share?

22 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Llama 3.1-405B has 42.

Related comparisons

Go deeper