# ERNIE 5.1 vs Llama 3.2 90B

> ERNIE 5.1 is the stronger model overall, scoring 43.8 to 27.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-llama-3-2-90b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where ERNIE 5.1 leads 40.3 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| Provider | Baidu | Meta |
| Noometry Index | 43.8 | 27.5 |
| Rank | 83 | 331 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 44.0 (#76)
- Llama 3.2 90B: —

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Coding | 1488 | — |

## Agentic & Tool Use

- ERNIE 5.1: —
- Llama 3.2 90B: 30.0 (#80)

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 21.9 (#211)
- Llama 3.2 90B: 21.7 (#217)

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| NYT Connections (extended) | 23.4% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1481 | — |
| Epoch Capabilities Index | — | 125.5 |

## Math

- ERNIE 5.1: 40.3 (#92)
- Llama 3.2 90B: 11.1 (#308)

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1481 | — |
| MATH Level 5 | — | 39.4% |

## Knowledge

- ERNIE 5.1: 41.9 (#102)
- Llama 3.2 90B: 21.7 (#274)

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| LMArena Expert | 1492 | — |
| MMLU | — | 80.3% |

## Multimodal

- ERNIE 5.1: —
- Llama 3.2 90B: 25.4 (#124)

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- ERNIE 5.1: 55.5 (#29)
- Llama 3.2 90B: —

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1454 | — |
| LMArena Chinese | 1508 | — |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1473 | — |

## Instruction Following

- ERNIE 5.1: 76.7 (#37)
- Llama 3.2 90B: —

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1460 | — |

## Long Context

- ERNIE 5.1: 44.7 (#59)
- Llama 3.2 90B: —

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1462 | — |

## Writing & Preference

- ERNIE 5.1: 65.1 (#52)
- Llama 3.2 90B: —

| Benchmark | ERNIE 5.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1468 | — |
| LMArena Creative Writing | 1441 | — |
| LMArena Multi-Turn | 1471 | — |

## FAQ

### Is ERNIE 5.1 better than Llama 3.2 90B?

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 27.5 on the Noometry Index.

### How many benchmarks do ERNIE 5.1 and Llama 3.2 90B share?

0 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Llama 3.2 90B has 9.