# GLM-4.5 vs Phi 3 Medium 4k Instruct

> GLM-4.5 is the stronger model overall, scoring 41.4 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and Phi 3 Medium 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5 leads 57.7 to 34.3.

## Snapshot

| | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 41.4 | 32.4 |
| Rank | 125 | 246 |
| Context | 131K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.1 (#121)
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1434 | 1130 |
| SWE-bench Verified (bash only) | 54.2% | — |
| WeirdML | 40.6% | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |

## Reasoning

- GLM-4.5: 27.7 (#99)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1127 |
| Kagi LLM Benchmark | 57.9% | — |

## Math

- GLM-4.5: 36.3 (#119)
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1427 | 1173 |

## Knowledge

- GLM-4.5: 35.5 (#172)
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1433 | 1108 |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |

## Multilingual

- GLM-4.5: 53.0 (#74)
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1417 | 1094 |
| LMArena Chinese | 1465 | 1108 |
| LMArena French | 1423 | 1109 |
| LMArena German | 1406 | 1101 |
| LMArena Japanese | 1416 | 1042 |
| LMArena Korean | 1382 | 954 |
| LMArena Russian | 1414 | 1145 |
| LMArena Spanish | 1454 | 1095 |

## Instruction Following

- GLM-4.5: 74.3 (#100)
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | 1114 |

## Long Context

- GLM-4.5: 38.2 (#196)
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1413 | 1120 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- GLM-4.5: 57.7 (#121)
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | GLM-4.5 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1430 | 1138 |
| LMArena Creative Writing | 1395 | 1106 |
| LMArena Multi-Turn | 1415 | 1088 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |

## FAQ

### Is GLM-4.5 better than Phi 3 Medium 4k Instruct?

GLM-4.5 is the stronger model overall, scoring 41.4 to 32.4 on the Noometry Index.

### Is GLM-4.5 or Phi 3 Medium 4k Instruct better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.1 versus 32.3 in the Noometry coding category.

### How many benchmarks do GLM-4.5 and Phi 3 Medium 4k Instruct share?

17 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.