# Hy4 preview vs Phi-4

> Hy4 preview is the stronger model overall, scoring 45.3 to 31.2 on the Noometry Index. Phi-4 costs 14× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/hy4-preview-vs-phi-4
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Hy4 preview leads 55.7 to 20.8.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Hy4 preview | Phi-4 |
|---|---|---|
| Provider | Tencent | Microsoft |
| Noometry Index | 45.3 | 31.2 |
| Rank | 73 | 279 |
| Context | 1.05M | 128K |
| Input $/M | $0.83 | $0.07 |
| Output $/M | $2.50 | $0.14 |
| Weights | Open | Open |

## Coding

- Hy4 preview: 51.6 (#38)
- Phi-4: 34.4 (#239)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| LMArena WebDev | 1632 | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| LMArena Coding | — | 1231 |
| BigCodeBench Complete | — | 55.4% |

## Agentic & Tool Use

- Hy4 preview: —
- Phi-4: 22.8 (#128)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Hy4 preview: 31.9 (#79)
- Phi-4: 17.7 (#291)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LMArena Hard Prompts | — | 1220 |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |

## Math

- Hy4 preview: 55.7 (#42)
- Phi-4: 20.8 (#285)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| ProofBench | 75% | — |
| LiveBench Math | — | 42% |
| LMArena Math | — | 1246 |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Hy4 preview: —
- Phi-4: 32.6 (#209)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| LMArena Expert | — | 1203 |
| MMLU | — | 84.8% |

## Multilingual

- Hy4 preview: —
- Phi-4: 37.2 (#237)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| LMArena Non-English | — | 1197 |
| LMArena Chinese | — | 1212 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Russian | — | 1209 |
| LMArena Spanish | — | 1234 |

## Instruction Following

- Hy4 preview: —
- Phi-4: 60.4 (#251)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | — | 58.4% |
| LMArena Instruction Following | — | 1201 |

## Long Context

- Hy4 preview: —
- Phi-4: 36.9 (#226)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| LMArena Longer Query | — | 1217 |

## Writing & Preference

- Hy4 preview: —
- Phi-4: 40.5 (#244)

| Benchmark | Hy4 preview | Phi-4 |
|---|---|---|
| LMArena Text | — | 1217 |
| LMArena Creative Writing | — | 1182 |
| Short-Story Creative Writing | — | 62.6% |
| LMArena Multi-Turn | — | 1206 |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Hy4 preview better than Phi-4?

Hy4 preview is the stronger model overall, scoring 45.3 to 31.2 on the Noometry Index. Phi-4 costs 14× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

### Which is cheaper, Hy4 preview or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Hy4 preview lists at $0.83 and $2.50.

### Is Hy4 preview or Phi-4 better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 128K.

### How many benchmarks do Hy4 preview and Phi-4 share?

0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Phi-4 has 37.