# GLM-4.5-Air vs Phi 3 Mini 4k Instruct

> GLM-4.5-Air is the stronger model overall, scoring 38.7 to 27.4 on the Noometry Index.

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

## Summary

- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 56.1 to 27.7.

## Snapshot

| | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 38.7 | 27.4 |
| Rank | 169 | 324 |
| Context | 131K | — |
| Input $/M | $0.20 | — |
| Output $/M | $1.10 | — |
| Weights | Open | Open |

## Coding

- GLM-4.5-Air: 34.5 (#225)
- Phi 3 Mini 4k Instruct: 26.1 (#319)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1397 | 1093 |
| GSO | 2.9% | — |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- GLM-4.5-Air: 23.3 (#166)
- Phi 3 Mini 4k Instruct: 13.6 (#326)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1072 |
| Kagi LLM Benchmark | 43% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| ForecastBench | 59.2 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- GLM-4.5-Air: 33.8 (#166)
- Phi 3 Mini 4k Instruct: 24.5 (#258)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1396 | 1111 |
| Omni-MATH | 39.1% | — |
| LiveBench Math | — | 15.7% |

## Knowledge

- GLM-4.5-Air: 34.6 (#184)
- Phi 3 Mini 4k Instruct: 27.9 (#241)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1370 | 1045 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- GLM-4.5-Air: 49.4 (#130)
- Phi 3 Mini 4k Instruct: 26.5 (#275)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1366 | 1021 |
| LMArena Chinese | 1427 | 1021 |
| LMArena French | 1399 | 1075 |
| LMArena German | 1376 | 1044 |
| LMArena Japanese | 1348 | 935 |
| LMArena Korean | 1306 | 905 |
| LMArena Russian | 1373 | 1022 |
| LMArena Spanish | 1385 | 1084 |

## Instruction Following

- GLM-4.5-Air: 69.8 (#165)
- Phi 3 Mini 4k Instruct: 48.0 (#298)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1353 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
| IFEval | 81.2% | — |

## Long Context

- GLM-4.5-Air: 41.6 (#130)
- Phi 3 Mini 4k Instruct: 31.7 (#271)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1367 | 1044 |

## Writing & Preference

- GLM-4.5-Air: 56.1 (#134)
- Phi 3 Mini 4k Instruct: 27.7 (#295)

| Benchmark | GLM-4.5-Air | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1384 | 1073 |
| LMArena Creative Writing | 1343 | 1037 |
| LMArena Multi-Turn | 1371 | 1018 |
| WildBench | 78.9% | — |
| LiveBench Language | — | 9.2% |

## FAQ

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

GLM-4.5-Air is the stronger model overall, scoring 38.7 to 27.4 on the Noometry Index.

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

GLM-4.5-Air scores higher on coding benchmarks: 34.5 versus 26.1 in the Noometry coding category.

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

17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.