# ERNIE 5.1 vs Phi 3 Small 8k Instruct

> ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 31.1.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Baidu | Microsoft |
| Noometry Index | 43.8 | 29.3 |
| Rank | 83 | 314 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 44.0 (#76)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1488 | 1101 |
| LiveBench Coding | — | 20.3% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Phi 3 Small 8k Instruct: —

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 21.9 (#211)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1100 |
| NYT Connections (extended) | 23.4% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- ERNIE 5.1: 40.3 (#92)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1481 | 1151 |
| LiveBench Math | — | 17.6% |

## Knowledge

- ERNIE 5.1: 41.9 (#102)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1492 | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- ERNIE 5.1: 55.5 (#29)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1454 | 1058 |
| LMArena Chinese | 1508 | 1061 |
| LMArena French | 1488 | 1135 |
| LMArena German | 1470 | 1080 |
| LMArena Japanese | 1422 | 966 |
| LMArena Korean | 1427 | 894 |
| LMArena Russian | 1459 | 1111 |
| LMArena Spanish | 1473 | 1111 |

## Instruction Following

- ERNIE 5.1: 76.7 (#37)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1460 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- ERNIE 5.1: 44.7 (#59)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1462 | 1088 |

## Writing & Preference

- ERNIE 5.1: 65.1 (#52)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | ERNIE 5.1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1468 | 1110 |
| LMArena Creative Writing | 1441 | 1083 |
| LMArena Multi-Turn | 1471 | 1068 |
| LiveBench Language | — | 12.9% |

## FAQ

### Is ERNIE 5.1 better than Phi 3 Small 8k Instruct?

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.3 on the Noometry Index.

### Is ERNIE 5.1 or Phi 3 Small 8k Instruct better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 27.9 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Phi 3 Small 8k Instruct has 32.