# GLM-4.6V vs Phi-2

> GLM-4.6V has enough public results to be ranked (#137); Phi-2 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/glm-4-6v-vs-phi-2
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Snapshot

| | GLM-4.6V | Phi-2 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 41.3 | — |
| Rank | 137 | — |
| Context | 128K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Open | Open |

## Coding

- GLM-4.6V: 40.9 (#128)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Coding | 1390 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- GLM-4.6V: 27.6 (#115)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1368 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.94 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |

## Knowledge

- GLM-4.6V: 38.0 (#149)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Expert | 1371 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |

## Multimodal

- GLM-4.6V: 34.8 (#90)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Vision | 1164 | — |

## Multilingual

- GLM-4.6V: 48.6 (#141)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1425 | — |
| LMArena Russian | 1340 | — |

## Instruction Following

- GLM-4.6V: 71.4 (#151)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1352 | — |

## Long Context

- GLM-4.6V: 41.3 (#143)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1358 | — |

## Writing & Preference

- GLM-4.6V: 56.6 (#137)
- Phi-2: —

| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Text | 1377 | — |
| LMArena Creative Writing | 1347 | — |
| LMArena Multi-Turn | 1360 | — |

## FAQ

### Is GLM-4.6V better than Phi-2?

GLM-4.6V has enough public results to be ranked (#137); Phi-2 does not yet, so treat this comparison as directional.

### How many benchmarks do GLM-4.6V and Phi-2 share?

0 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Phi-2 has 11.