Model comparison
GLM-4.5 vs Phi-4 Mini
GLM-4.5 is the stronger model overall, scoring 42.0 to 30.9 on the Noometry Index. Phi-4 Mini costs 7.6× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in coding, where GLM-4.5 leads 41.4 to 28.1.
- Phi-4 Mini is cheaper at $0.075 / $0.30 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-4.5 | Phi-4 Mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 42.0 | 30.9 |
| Released | 2025-07-27 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 98K | 4K |
| Input $ / M tokens | $0.60 | $0.075 |
| Output $ / M tokens | $2.20 | $0.30 |
| Results tracked | 27 | 3 |
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 Mini: 28.1 (#317)
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| SWE-bench Verified (bash only) | 54.2% | — |
| SciCode | — | 10.8% |
| WeirdML | 40.6% | — |
| LMArena Coding | 1434 | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Reasoning GLM-4.5 leads
GLM-4.5: 28.6 (#100), Phi-4 Mini: 22.4 (#195)
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1429 | — |
Math Not comparable
GLM-4.5: 39.0 (#116), Phi-4 Mini: —
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1427 | — |
Knowledge GLM-4.5 leads
GLM-4.5: 35.9 (#179), Phi-4 Mini: 25.3 (#262)
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1433 | — |
Multilingual Not comparable
GLM-4.5: 52.8 (#77), Phi-4 Mini: —
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1418 | — |
| LMArena German | 1407 | — |
| LMArena Japanese | 1415 | — |
| LMArena Korean | 1380 | — |
| LMArena Russian | 1414 | — |
| LMArena Spanish | 1454 | — |
Instruction Following Not comparable
GLM-4.5: 74.1 (#104), Phi-4 Mini: —
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1404 | — |
Long Context Not comparable
GLM-4.5: 38.2 (#201), Phi-4 Mini: —
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| Fiction.LiveBench | 58.3% | — |
| LMArena Longer Query | 1412 | — |
Writing & Preference Not comparable
GLM-4.5: 57.5 (#127), Phi-4 Mini: —
| Benchmark | GLM-4.5 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1430 | — |
| LMArena Creative Writing | 1395 | — |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
| LMArena Multi-Turn | 1415 | — |
Frequently asked questions
Is GLM-4.5 better than Phi-4 Mini?
GLM-4.5 is the stronger model overall, scoring 42.0 to 30.9 on the Noometry Index. Phi-4 Mini costs 7.6× 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 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Is GLM-4.5 or Phi-4 Mini better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 28.1 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 Mini share?
0 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Phi-4 Mini has 3.