# GLM-4.5 vs phi-3-medium 14B

> GLM-4.5 is the stronger model overall, scoring 42.0 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-phi-3-medium-14b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where GLM-4.5 leads 35.9 to 9.1.

## Snapshot

| | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 42.0 | 29.7 |
| Rank | 122 | 306 |
| Context | 131K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.4 (#125)
- phi-3-medium 14B: 36.8 (#201)

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified (bash only) | 54.2% | — |
| WeirdML | 40.6% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1434 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |

## Reasoning

- GLM-4.5: 28.6 (#100)
- phi-3-medium 14B: —

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | — |
| LMArena Hard Prompts | 1429 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- GLM-4.5: 39.0 (#116)
- phi-3-medium 14B: 27.3 (#250)

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1427 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- GLM-4.5: 35.9 (#179)
- phi-3-medium 14B: 9.1 (#306)

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| LMArena Expert | 1433 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- GLM-4.5: 52.8 (#77)
- phi-3-medium 14B: —

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| 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

- GLM-4.5: 74.1 (#104)
- phi-3-medium 14B: —

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1404 | — |

## Long Context

- GLM-4.5: 38.2 (#201)
- phi-3-medium 14B: —

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 58.3% | — |
| LMArena Longer Query | 1412 | — |

## Writing & Preference

- GLM-4.5: 57.5 (#127)
- phi-3-medium 14B: —

| Benchmark | GLM-4.5 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1430 | — |
| LMArena Creative Writing | 1395 | — |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
| LMArena Multi-Turn | 1415 | — |

## FAQ

### Is GLM-4.5 better than phi-3-medium 14B?

GLM-4.5 is the stronger model overall, scoring 42.0 to 29.7 on the Noometry Index.

### Is GLM-4.5 or phi-3-medium 14B better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 36.8 in the Noometry coding category.

### How many benchmarks do GLM-4.5 and phi-3-medium 14B share?

0 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and phi-3-medium 14B has 13.