# GLM-5.1 vs Phi-4

> GLM-5.1 is the stronger model overall, scoring 47.8 to 31.2 on the Noometry Index. Phi-4 costs 25× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-phi-4
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 13.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 128K.

## Snapshot

| | GLM-5.1 | Phi-4 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 47.8 | 31.2 |
| Rank | 59 | 279 |
| Context | 200K | 128K |
| Input $/M | $1.40 | $0.07 |
| Output $/M | $4.40 | $0.14 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.7 (#55)
- Phi-4: 34.4 (#239)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| LMArena Coding | 1485 | 1231 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Phi-4: 22.8 (#128)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Phi-4: 17.7 (#291)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| Chess Puzzles | 19% | 1% |
| LMArena Hard Prompts | 1472 | 1220 |
| Epoch Capabilities Index | 149.84 | 130.42 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| LiveBench | — | 41.6% |

## Math

- GLM-5.1: 49.7 (#60)
- Phi-4: 20.8 (#285)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 13.8% |
| LMArena Math | 1473 | 1246 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Phi-4: 32.6 (#209)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| GPQA Diamond | 89.9% | 56.1% |
| LMArena Expert | 1476 | 1203 |
| SimpleQA Verified | 34% | — |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Phi-4: 37.2 (#237)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| LMArena Non-English | 1447 | 1197 |
| LMArena Chinese | 1515 | 1212 |
| LMArena French | 1474 | 1224 |
| LMArena German | 1465 | 1222 |
| LMArena Japanese | 1434 | 1158 |
| LMArena Korean | 1418 | 1151 |
| LMArena Russian | 1454 | 1209 |
| LMArena Spanish | 1469 | 1234 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Phi-4: 60.4 (#251)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- GLM-5.1: 44.9 (#53)
- Phi-4: 36.9 (#226)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1466 | 1217 |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Phi-4: 40.5 (#244)

| Benchmark | GLM-5.1 | Phi-4 |
|---|---|---|
| LMArena Text | 1461 | 1217 |
| LMArena Creative Writing | 1453 | 1182 |
| LMArena Multi-Turn | 1472 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 1592 | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is GLM-5.1 better than Phi-4?

GLM-5.1 is the stronger model overall, scoring 47.8 to 31.2 on the Noometry Index. Phi-4 costs 25× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.1 or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Phi-4 better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 128K.

### How many benchmarks do GLM-5.1 and Phi-4 share?

21 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Phi-4 has 37.