# GLM-4.7-Flash vs Phi-4

> GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 30.9 on the Noometry Index. Phi-4 costs 1.7× less per token, which makes it the better buy when GLM-4.7-Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-7-flash-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GLM-4.7-Flash scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.7-Flash leads 34.4 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 13.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.06 / $0.40 for GLM-4.7-Flash.
- GLM-4.7-Flash accepts more context: 200K tokens versus 128K.

## Snapshot

| | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 38.4 | 30.9 |
| Rank | 175 | 269 |
| Context | 200K | 128K |
| Input $/M | $0.06 | $0.07 |
| Output $/M | $0.40 | $0.14 |
| Weights | Open | Open |

## Coding

- GLM-4.7-Flash: 40.0 (#133)
- Phi-4: 33.8 (#237)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| LMArena Coding | 1383 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |

## Agentic & Tool Use

- GLM-4.7-Flash: —
- Phi-4: 22.6 (#120)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- GLM-4.7-Flash: 20.2 (#224)
- Phi-4: 17.0 (#287)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| Chess Puzzles | 0% | 1% |
| LMArena Hard Prompts | 1356 | 1220 |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.43 |
| LiveBench | — | 41.6% |

## Math

- GLM-4.7-Flash: 34.4 (#159)
- Phi-4: 19.6 (#279)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3% | 13.8% |
| LMArena Math | 1354 | 1246 |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |

## Knowledge

- GLM-4.7-Flash: 35.4 (#177)
- Phi-4: 32.5 (#204)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| GPQA Diamond | 60.5% | 56.1% |
| Vectara Hallucination Rate | 9.3% | 3.7% |
| LMArena Expert | 1357 | 1203 |
| Confabulations | — | 29.4% |
| MMLU | — | 84.8% |

## Multilingual

- GLM-4.7-Flash: 46.8 (#152)
- Phi-4: 37.4 (#232)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| LMArena Non-English | 1331 | 1197 |
| LMArena Chinese | 1403 | 1211 |
| LMArena French | 1332 | 1223 |
| LMArena German | 1336 | 1222 |
| LMArena Korean | 1284 | 1151 |
| LMArena Russian | 1333 | 1209 |
| LMArena Spanish | 1351 | 1234 |
| LMArena Japanese | — | 1158 |

## Instruction Following

- GLM-4.7-Flash: 70.3 (#162)
- Phi-4: 60.6 (#246)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1327 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- GLM-4.7-Flash: 40.9 (#143)
- Phi-4: 36.9 (#221)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1345 | 1217 |

## Writing & Preference

- GLM-4.7-Flash: 47.7 (#206)
- Phi-4: 40.7 (#239)

| Benchmark | GLM-4.7-Flash | Phi-4 |
|---|---|---|
| LMArena Text | 1351 | 1217 |
| LMArena Creative Writing | 1297 | 1182 |
| LMArena Multi-Turn | 1342 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 1125 | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is GLM-4.7-Flash better than Phi-4?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 30.9 on the Noometry Index. Phi-4 costs 1.7× less per token, which makes it the better buy when GLM-4.7-Flash's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.7-Flash or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; GLM-4.7-Flash lists at $0.06 and $0.40.

### Is GLM-4.7-Flash or Phi-4 better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 128K.

### How many benchmarks do GLM-4.7-Flash and Phi-4 share?

20 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Phi-4 has 37.