# ERNIE 5.1 vs Grok-3 mini

> ERNIE 5.1 is the stronger model overall, scoring 43.1 to 41.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 5 categories and Grok-3 mini in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 52.7.

## Snapshot

| | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| Provider | Baidu | xAI |
| Noometry Index | 43.1 | 41.0 |
| Rank | 87 | 130 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.1: 43.4 (#78)
- Grok-3 mini: 40.4 (#126)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1488 | 1380 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Grok-3 mini: —

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- Grok-3 mini: 13.8 (#323)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1374 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |

## Math

- ERNIE 5.1: 37.5 (#96)
- Grok-3 mini: 40.3 (#78)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Math | 1481 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- Grok-3 mini: 46.3 (#75)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1491 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- Grok-3 mini: 48.3 (#141)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1455 | 1352 |
| LMArena Chinese | 1507 | 1387 |
| LMArena French | 1486 | 1357 |
| LMArena German | 1470 | 1350 |
| LMArena Japanese | 1422 | 1343 |
| LMArena Korean | 1428 | 1336 |
| LMArena Russian | 1459 | 1352 |
| LMArena Spanish | 1472 | 1379 |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- Grok-3 mini: 78.7 (#8)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1460 | 1356 |
| IFEval | — | 95.1% |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- Grok-3 mini: 41.0 (#142)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1462 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- Grok-3 mini: 52.7 (#163)

| Benchmark | ERNIE 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1468 | 1370 |
| LMArena Creative Writing | 1440 | 1342 |
| LMArena Multi-Turn | 1471 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |

## FAQ

### Is ERNIE 5.1 better than Grok-3 mini?

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 41.0 on the Noometry Index.

### Is ERNIE 5.1 or Grok-3 mini better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 40.4 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Grok-3 mini share?

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Grok-3 mini has 35.