Noometry

Model comparison

GLM-4.7 vs Llama 2-13B

GLM-4.7 is the stronger model overall, scoring 42.0 to 29.6 on the Noometry Index.

Last verified . 19 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Llama 2-13B Meta

29.6

Rank #309 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.7 leads 60.9 to 29.8.
  • The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 0% for Llama 2-13B.

Side by side

GLM-4.7Llama 2-13B
ProviderZ.ai (Zhipu)Meta
Noometry Index42.029.6
Released2025-12-222023-07-18
WeightsOpenOpen
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked3632

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 2-13B: 30.9 (#291)

BenchmarkGLM-4.7Llama 2-13B
LMArena Coding14541062
LMArena WebDev1435—
SciCode45.1%—
ALE-Bench399.48—

Agentic & Tool Use Not comparable

GLM-4.7: 26.5 (#103), Llama 2-13B: —

BenchmarkGLM-4.7Llama 2-13B
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 24.3 (#164), Llama 2-13B: 12.8 (#337)

BenchmarkGLM-4.7Llama 2-13B
Chess Puzzles6%0%
LMArena Hard Prompts14431051
Epoch Capabilities Index143.51106.17
SimpleBench47.7%—
CritPt1.7%—
DTBench—42.2%
BIG-Bench Hard—58.2%
HellaSwag—80.7%
LAMBADA—76.5%
PIQA—80.8%
WinoGrande—72.8%

Math GLM-4.7 leads

GLM-4.7: 38.6 (#135), Llama 2-13B: 31.1 (#229)

BenchmarkGLM-4.7Llama 2-13B
LMArena Math14231065
OTIS Mock AIME 2024-202583.3%—
ProofBench6%—
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—
GSM8K—36.9%

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#80), Llama 2-13B: 28.1 (#249)

BenchmarkGLM-4.7Llama 2-13B
LMArena Expert14241030
GPQA Diamond83.3%—
SimpleQA Verified32.2%—
Vectara Hallucination Rate11.7%—
ARC (AI2) Challenge—60.3%
BoolQ—82.4%
MMLU—55.6%
OpenBookQA—57%
TriviaQA—79.6%

Multimodal Not comparable

GLM-4.7: —, Llama 2-13B: —

BenchmarkGLM-4.7Llama 2-13B
ScienceQA—55.8%

Multilingual GLM-4.7 leads

GLM-4.7: 52.8 (#79), Llama 2-13B: 26.5 (#279)

BenchmarkGLM-4.7Llama 2-13B
LMArena Non-English14171024
LMArena Chinese14951001
LMArena French14321044
LMArena German14241009
LMArena Japanese1439894
LMArena Korean1399953
LMArena Russian14231055
LMArena Spanish14341087

Instruction Following GLM-4.7 leads

GLM-4.7: 74.4 (#95), Llama 2-13B: 53.3 (#287)

BenchmarkGLM-4.7Llama 2-13B
LMArena Instruction Following14111045

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#116), Llama 2-13B: 32.3 (#269)

BenchmarkGLM-4.7Llama 2-13B
LMArena Longer Query14321064
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 60.9 (#93), Llama 2-13B: 29.8 (#289)

BenchmarkGLM-4.7Llama 2-13B
LMArena Text14351084
LMArena Creative Writing14011047
LMArena Multi-Turn14461050
EQ-Bench Creative Writing1413—

Frequently asked questions

Is GLM-4.7 better than Llama 2-13B?

GLM-4.7 is the stronger model overall, scoring 42.0 to 29.6 on the Noometry Index.

Is GLM-4.7 or Llama 2-13B better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 30.9 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Llama 2-13B share?

19 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Llama 2-13B has 32.

Related comparisons

Go deeper