Noometry

Model comparison

GLM-4.6V vs Phi-4

GLM-4.6V is the stronger model overall, scoring 41.3 to 31.2 on the Noometry Index. Phi-4 costs 5.1× less per token, which makes it the better buy when GLM-4.6V's lead doesn't matter for your workload.

Last verified . 11 shared benchmarks.

GLM-4.6V Z.ai (Zhipu)

41.3

Rank #137 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 7 categories and Phi-4 in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.6V leads 56.6 to 40.5.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.30 / $0.90 for GLM-4.6V.

Side by side

GLM-4.6VPhi-4
ProviderZ.ai (Zhipu)Microsoft
Noometry Index41.331.2
Released2025-12-082024-12-11
WeightsOpenOpen
Context window128K128K
Max output33K4K
Input $ / M tokens$0.30$0.07
Output $ / M tokens$0.90$0.14
Results tracked1237

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

Category by category

Coding GLM-4.6V leads

GLM-4.6V: 40.9 (#128), Phi-4: 34.4 (#239)

BenchmarkGLM-4.6VPhi-4
LMArena Coding13901231
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%

Agentic & Tool Use Not comparable

GLM-4.6V: —, Phi-4: 22.8 (#128)

BenchmarkGLM-4.6VPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning GLM-4.6V leads

GLM-4.6V: 27.6 (#115), Phi-4: 17.7 (#291)

BenchmarkGLM-4.6VPhi-4
LMArena Hard Prompts13681220
Chess Puzzles—1%
LiveBench Reasoning—47.8%
LiveBench Data Analysis—45.2%
Epoch Capabilities Index—130.42
LiveBench—41.6%

Math Not comparable

GLM-4.6V: —, Phi-4: 20.8 (#285)

BenchmarkGLM-4.6VPhi-4
OTIS Mock AIME 2024-2025—13.8%
LiveBench Math—42%
LMArena Math—1246
MATH Level 5—64.9%

Knowledge GLM-4.6V leads

GLM-4.6V: 38.0 (#149), Phi-4: 32.6 (#209)

BenchmarkGLM-4.6VPhi-4
LMArena Expert13711203
GPQA Diamond—56.1%
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multimodal Not comparable

GLM-4.6V: 34.8 (#90), Phi-4: —

BenchmarkGLM-4.6VPhi-4
LMArena Vision1164—

Multilingual GLM-4.6V leads

GLM-4.6V: 48.6 (#141), Phi-4: 37.2 (#237)

BenchmarkGLM-4.6VPhi-4
LMArena Non-English13591197
LMArena Chinese14251212
LMArena Russian13401209
LMArena French—1224
LMArena German—1222
LMArena Japanese—1158
LMArena Korean—1151
LMArena Spanish—1234

Instruction Following GLM-4.6V leads

GLM-4.6V: 71.4 (#151), Phi-4: 60.4 (#251)

BenchmarkGLM-4.6VPhi-4
LMArena Instruction Following13521201
LiveBench Instruction Following—58.4%

Long Context GLM-4.6V leads

GLM-4.6V: 41.3 (#143), Phi-4: 36.9 (#226)

BenchmarkGLM-4.6VPhi-4
LMArena Longer Query13581217

Writing & Preference GLM-4.6V leads

GLM-4.6V: 56.6 (#137), Phi-4: 40.5 (#244)

BenchmarkGLM-4.6VPhi-4
LMArena Text13771217
LMArena Creative Writing13471182
LMArena Multi-Turn13601206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is GLM-4.6V better than Phi-4?

GLM-4.6V is the stronger model overall, scoring 41.3 to 31.2 on the Noometry Index. Phi-4 costs 5.1× less per token, which makes it the better buy when GLM-4.6V's lead doesn't matter for your workload.

Which is cheaper, GLM-4.6V or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; GLM-4.6V lists at $0.30 and $0.90.

Is GLM-4.6V or Phi-4 better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.9 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Both accept 128K tokens.

How many benchmarks do GLM-4.6V and Phi-4 share?

11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper