Noometry

Model comparison

GLM-4.5 vs Phi-4

GLM-4.5 is the stronger model overall, scoring 42.0 to 31.2 on the Noometry Index. Phi-4 costs 11× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.5 leads 39.0 to 20.8.
  • The biggest single-benchmark swing is Confabulations: 11.3% for GLM-4.5 and 29.4% for Phi-4.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
  • GLM-4.5 accepts more context: 131K tokens versus 128K.

Side by side

GLM-4.5Phi-4
ProviderZ.ai (Zhipu)Microsoft
Noometry Index42.031.2
Released2025-07-272024-12-11
WeightsOpenOpen
Context window131K128K
Max output98K4K
Input $ / M tokens$0.60$0.07
Output $ / M tokens$2.20$0.14
Results tracked2737

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

Category by category

Coding GLM-4.5 leads

GLM-4.5: 41.4 (#125), Phi-4: 34.4 (#239)

BenchmarkGLM-4.5Phi-4
LMArena Coding14341231
SWE-bench Verified (bash only)54.2%—
WeirdML40.6%—
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%
ALE-Bench344.82—
AlgoTune1.52—

Agentic & Tool Use Not comparable

GLM-4.5: —, Phi-4: 22.8 (#128)

BenchmarkGLM-4.5Phi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning GLM-4.5 leads

GLM-4.5: 28.6 (#100), Phi-4: 17.7 (#291)

BenchmarkGLM-4.5Phi-4
LMArena Hard Prompts14291220
Kagi LLM Benchmark57.9%—
Chess Puzzles—1%
LiveBench Reasoning—47.8%
LiveBench Data Analysis—45.2%
Epoch Capabilities Index—130.42
LiveBench—41.6%

Math GLM-4.5 leads

GLM-4.5: 39.0 (#116), Phi-4: 20.8 (#285)

BenchmarkGLM-4.5Phi-4
LMArena Math14271246
OTIS Mock AIME 2024-2025—13.8%
LiveBench Math—42%
MATH Level 5—64.9%

Knowledge GLM-4.5 leads

GLM-4.5: 35.9 (#179), Phi-4: 32.6 (#209)

BenchmarkGLM-4.5Phi-4
Confabulations11.3%29.4%
LMArena Expert14331203
GPQA Diamond—56.1%
Humanity's Last Exam8.3%—
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multilingual GLM-4.5 leads

GLM-4.5: 52.8 (#77), Phi-4: 37.2 (#237)

BenchmarkGLM-4.5Phi-4
LMArena Non-English14171197
LMArena Chinese14651212
LMArena French14181224
LMArena German14071222
LMArena Japanese14151158
LMArena Korean13801151
LMArena Russian14141209
LMArena Spanish14541234

Instruction Following GLM-4.5 leads

GLM-4.5: 74.1 (#104), Phi-4: 60.4 (#251)

BenchmarkGLM-4.5Phi-4
LMArena Instruction Following14041201
LiveBench Instruction Following—58.4%

Long Context GLM-4.5 leads

GLM-4.5: 38.2 (#201), Phi-4: 36.9 (#226)

BenchmarkGLM-4.5Phi-4
LMArena Longer Query14121217
Fiction.LiveBench58.3%—

Writing & Preference GLM-4.5 leads

GLM-4.5: 57.5 (#127), Phi-4: 40.5 (#244)

BenchmarkGLM-4.5Phi-4
LMArena Text14301217
LMArena Creative Writing13951182
Short-Story Creative Writing73.4%62.6%
LMArena Multi-Turn14151206
EQ-Bench Creative Writing1343—
LiveBench Language—25.6%

Frequently asked questions

Is GLM-4.5 better than Phi-4?

GLM-4.5 is the stronger model overall, scoring 42.0 to 31.2 on the Noometry Index. Phi-4 costs 11× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

Which is cheaper, GLM-4.5 or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

Is GLM-4.5 or Phi-4 better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

GLM-4.5 does, with 131K tokens against 128K.

How many benchmarks do GLM-4.5 and Phi-4 share?

19 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper