Noometry

Model comparison

GLM-4.7 vs Phi 3 Small 8k Instruct

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.8 on the Noometry Index.

Last verified . 17 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

Phi 3 Small 8k Instruct Microsoft

28.8

Rank #310 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.7 leads 61.1 to 31.3.

Side by side

GLM-4.7Phi 3 Small 8k Instruct
ProviderZ.ai (Zhipu)Microsoft
Noometry Index41.728.8
Released2025-12-222024-04-23
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: 43.6 (#74), Phi 3 Small 8k Instruct: 27.4 (#313)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Coding14541102
LMArena WebDev1435—
SciCode45.1%—
LiveBench Coding—20.3%
ALE-Bench399.48—

Agentic & Tool Use Not comparable

GLM-4.7: 26.4 (#96), Phi 3 Small 8k Instruct: —

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 23.7 (#161), Phi 3 Small 8k Instruct: 14.2 (#319)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Hard Prompts14431100
SimpleBench47.7%—
CritPt1.7%—
Chess Puzzles6%—
LiveBench Reasoning—15.9%
LiveBench Data Analysis—30.3%
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
Epoch Capabilities Index143.53—
HellaSwag—77%
LiveBench—24%
WinoGrande—81.5%

Math GLM-4.7 leads

GLM-4.7: 37.7 (#92), Phi 3 Small 8k Instruct: 25.4 (#247)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Math14231151
OTIS Mock AIME 2024-202583.3%—
ProofBench6%—
LiveBench Math—17.6%
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#74), Phi 3 Small 8k Instruct: 28.5 (#237)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Expert14241067
GPQA Diamond83.3%—
SimpleQA Verified32.2%—
Vectara Hallucination Rate11.7%—
ARC (AI2) Challenge—90.7%
MMLU—75.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual GLM-4.7 leads

GLM-4.7: 53.0 (#75), Phi 3 Small 8k Instruct: 28.6 (#267)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Non-English14171058
LMArena Chinese14951061
LMArena French14321134
LMArena German14261080
LMArena Japanese1439966
LMArena Korean1401894
LMArena Russian14231111
LMArena Spanish14331111

Instruction Following GLM-4.7 leads

GLM-4.7: 74.6 (#90), Phi 3 Small 8k Instruct: 52.2 (#287)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Instruction Following14111087
LiveBench Instruction Following—47.2%

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#111), Phi 3 Small 8k Instruct: 33.0 (#262)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Longer Query14321088
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 61.1 (#89), Phi 3 Small 8k Instruct: 31.3 (#279)

BenchmarkGLM-4.7Phi 3 Small 8k Instruct
LMArena Text14361110
LMArena Creative Writing14011083
LMArena Multi-Turn14461068
EQ-Bench Creative Writing1413—
LiveBench Language—12.9%

Frequently asked questions

Is GLM-4.7 better than Phi 3 Small 8k Instruct?

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.8 on the Noometry Index.

Is GLM-4.7 or Phi 3 Small 8k Instruct better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 27.4 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper