# ERNIE 5.1 vs Magistral Small

> ERNIE 5.1 is the stronger model overall, scoring 43.1 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-magistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where ERNIE 5.1 leads 20.9 to 6.9.
- Magistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Magistral Small |
|---|---|---|
| Provider | Baidu | Mistral AI |
| Noometry Index | 43.1 | 29.9 |
| Rank | 87 | 289 |
| Context | — | 128K |
| Input $/M | — | $0.50 |
| Output $/M | — | $1.50 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 43.4 (#78)
- Magistral Small: 37.8 (#172)

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| SciCode | — | 35.2% |
| LMArena Coding | 1488 | — |

## Agentic & Tool Use

- ERNIE 5.1: —
- Magistral Small: —

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- Magistral Small: 6.9 (#345)

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 6.3% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 3% |
| LMArena Hard Prompts | 1481 | — |
| DTBench | — | 61.3% |
| Epoch Capabilities Index | — | 133.19 |

## Math

- ERNIE 5.1: 37.5 (#96)
- Magistral Small: 24.9 (#253)

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 30% |
| LMArena Math | 1481 | — |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- Magistral Small: 30.9 (#215)

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | 1491 | — |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- Magistral Small: —

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| LMArena Non-English | 1455 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1486 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1428 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1472 | — |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- Magistral Small: —

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| LMArena Instruction Following | 1460 | — |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- Magistral Small: —

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1462 | — |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- Magistral Small: —

| Benchmark | ERNIE 5.1 | Magistral Small |
|---|---|---|
| LMArena Text | 1468 | — |
| LMArena Creative Writing | 1440 | — |
| LMArena Multi-Turn | 1471 | — |

## FAQ

### Is ERNIE 5.1 better than Magistral Small?

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 29.9 on the Noometry Index.

### Is ERNIE 5.1 or Magistral Small better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 37.8 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Magistral Small share?

0 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Magistral Small has 10.