# ERNIE 5.1 vs Grok 4.7

> Grok 4.7 is the stronger model overall, scoring 46.6 to 43.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-grok-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. ERNIE 5.1 scores higher in 4 categories and Grok 4.7 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 40.1 to 20.9.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 76.8% for Grok 4.7.

## Snapshot

| | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| Provider | Baidu | xAI |
| Noometry Index | 43.1 | 46.6 |
| Rank | 87 | 56 |
| Context | — | 500K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.1: 43.4 (#78)
- Grok 4.7: 55.0 (#23)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Coding | 1488 | 1423 |
| CursorBench | — | 46.3% |
| LMArena WebDev | — | 1636 |
| FrontierSWE | — | 29.5% |
| SciCode | — | 57.4% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Grok 4.7: —

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- Grok 4.7: 40.1 (#49)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| NYT Connections (extended) | 23.4% | 76.8% |
| LMArena Hard Prompts | 1481 | 1409 |
| CritPt | — | 17.7% |

## Math

- ERNIE 5.1: 37.5 (#96)
- Grok 4.7: 41.1 (#73)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Math | 1481 | 1393 |
| ProofBench | — | 34% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- Grok 4.7: 38.7 (#130)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Expert | 1491 | 1413 |

## Multimodal

- ERNIE 5.1: —
- Grok 4.7: 28.8 (#107)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| Furniture Assembly | — | 20.8% |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- Grok 4.7: 51.2 (#108)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1455 | 1392 |
| LMArena Chinese | 1507 | 1476 |
| LMArena Russian | 1459 | 1396 |
| LMArena French | 1486 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1428 | — |
| LMArena Spanish | 1472 | — |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- Grok 4.7: 74.3 (#98)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1406 |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- Grok 4.7: 43.2 (#97)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1462 | 1416 |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- Grok 4.7: 70.1 (#23)

| Benchmark | ERNIE 5.1 | Grok 4.7 |
|---|---|---|
| LMArena Text | 1468 | 1397 |
| LMArena Creative Writing | 1440 | 1391 |
| LMArena Multi-Turn | 1471 | 1389 |
| EQ-Bench Creative Writing | — | 2007 |

## FAQ

### Is ERNIE 5.1 better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 46.6 to 43.1 on the Noometry Index.

### Is ERNIE 5.1 or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 43.4 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Grok 4.7 share?

13 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Grok 4.7 has 21.