# GLM-4.7-Flash vs Phi 3 Mini 4k Instruct

> GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-flash-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-4.7-Flash 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 instruction following, where GLM-4.7-Flash leads 70.1 to 47.7.

## Snapshot

| | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 38.8 | 27.9 |
| Rank | 180 | 328 |
| Context | 200K | — |
| Input $/M | $0.06 | — |
| Output $/M | $0.40 | — |
| Weights | Open | Open |

## Coding

- GLM-4.7-Flash: 40.6 (#135)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1383 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- GLM-4.7-Flash: 20.9 (#229)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1356 | 1072 |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- GLM-4.7-Flash: 36.1 (#173)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1355 | 1111 |
| OTIS Mock AIME 2024-2025 | 58.3% | — |
| LiveBench Math | — | 15.7% |

## Knowledge

- GLM-4.7-Flash: 35.5 (#184)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1357 | 1045 |
| GPQA Diamond | 60.5% | — |
| Vectara Hallucination Rate | 9.3% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- GLM-4.7-Flash: 46.5 (#158)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1330 | 1021 |
| LMArena Chinese | 1403 | 1021 |
| LMArena French | 1332 | 1076 |
| LMArena German | 1337 | 1044 |
| LMArena Korean | 1283 | 905 |
| LMArena Russian | 1332 | 1022 |
| LMArena Spanish | 1350 | 1085 |
| LMArena Japanese | — | 935 |

## Instruction Following

- GLM-4.7-Flash: 70.1 (#167)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1327 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- GLM-4.7-Flash: 40.9 (#148)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1345 | 1044 |

## Writing & Preference

- GLM-4.7-Flash: 47.4 (#210)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | GLM-4.7-Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1351 | 1073 |
| LMArena Creative Writing | 1297 | 1037 |
| LMArena Multi-Turn | 1342 | 1018 |
| EQ-Bench Creative Writing | 1125 | — |
| LiveBench Language | — | 9.2% |

## FAQ

### Is GLM-4.7-Flash better than Phi 3 Mini 4k Instruct?

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 27.9 on the Noometry Index.

### Is GLM-4.7-Flash or Phi 3 Mini 4k Instruct better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 26.6 in the Noometry coding category.

### How many benchmarks do GLM-4.7-Flash and Phi 3 Mini 4k Instruct share?

17 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.