Noometry

Model comparison

GLM-4.7 vs Llama 2-7B

GLM-4.7 is the stronger model overall, scoring 42.0 to 29.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Llama 2-7B Meta

29.1

Rank #317 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Llama 2-7B 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 28.0.
  • The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 0% for Llama 2-7B.

Side by side

GLM-4.7Llama 2-7B
ProviderZ.ai (Zhipu)Meta
Noometry Index42.029.1
Released2025-12-222023-07-18
WeightsOpenOpen
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked3629

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 2-7B: 29.2 (#307)

BenchmarkGLM-4.7Llama 2-7B
LMArena Coding14541002
LMArena WebDev1435—
SciCode45.1%—
ALE-Bench399.48—

Agentic & Tool Use Not comparable

GLM-4.7: 26.5 (#103), Llama 2-7B: —

BenchmarkGLM-4.7Llama 2-7B
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 24.3 (#164), Llama 2-7B: 15.7 (#312)

BenchmarkGLM-4.7Llama 2-7B
Chess Puzzles6%0%
LMArena Hard Prompts14431009
Epoch Capabilities Index143.5199.06
SimpleBench47.7%—
CritPt1.7%—
BIG-Bench Hard—39.2%
HellaSwag—77.2%
LAMBADA—73.3%
PIQA—78.8%
WinoGrande—69.2%

Math GLM-4.7 leads

GLM-4.7: 38.6 (#135), Llama 2-7B: 30.7 (#233)

BenchmarkGLM-4.7Llama 2-7B
LMArena Math14231042
OTIS Mock AIME 2024-202583.3%—
ProofBench6%—
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—
GSM8K—16.7%

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#80), Llama 2-7B: 28.2 (#248)

BenchmarkGLM-4.7Llama 2-7B
LMArena Expert14241036
GPQA Diamond83.3%—
SimpleQA Verified32.2%—
Vectara Hallucination Rate11.7%—
ARC (AI2) Challenge—45.9%
BoolQ—77.9%
MMLU—45.8%
OpenBookQA—58.6%
TriviaQA—73.7%

Multimodal Not comparable

GLM-4.7: —, Llama 2-7B: —

BenchmarkGLM-4.7Llama 2-7B
ScienceQA—43.1%

Multilingual GLM-4.7 leads

GLM-4.7: 52.8 (#79), Llama 2-7B: 23.8 (#293)

BenchmarkGLM-4.7Llama 2-7B
LMArena Non-English1417973
LMArena Chinese1495973
LMArena French1432970
LMArena German1424978
LMArena Russian1423995
LMArena Spanish14341007
LMArena Japanese1439—
LMArena Korean1399—

Instruction Following GLM-4.7 leads

GLM-4.7: 74.4 (#95), Llama 2-7B: 50.8 (#298)

BenchmarkGLM-4.7Llama 2-7B
LMArena Instruction Following14111006

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#116), Llama 2-7B: 30.4 (#287)

BenchmarkGLM-4.7Llama 2-7B
LMArena Longer Query1432999
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 60.9 (#93), Llama 2-7B: 28.0 (#298)

BenchmarkGLM-4.7Llama 2-7B
LMArena Text14351053
LMArena Creative Writing14011033
LMArena Multi-Turn14461029
EQ-Bench Creative Writing1413—

Frequently asked questions

Is GLM-4.7 better than Llama 2-7B?

GLM-4.7 is the stronger model overall, scoring 42.0 to 29.1 on the Noometry Index.

Is GLM-4.7 or Llama 2-7B better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 29.2 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Llama 2-7B share?

17 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Llama 2-7B has 29.

Related comparisons

Go deeper