# ERNIE 5.1 vs Grok 3

> ERNIE 5.1 is the stronger model overall, scoring 43.8 to 39.9 on the Noometry Index.

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

## Summary

- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Grok 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 55.8.

## Snapshot

| | ERNIE 5.1 | Grok 3 |
|---|---|---|
| Provider | Baidu | xAI |
| Noometry Index | 43.8 | 39.9 |
| Rank | 83 | 157 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.1: 44.0 (#76)
- Grok 3: 41.9 (#115)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Coding | 1488 | 1432 |
| Aider Polyglot | — | 53.3% |
| WeirdML | — | 37.2% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Grok 3: 30.5 (#76)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| BALROG | — | 29.5% |
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 21.9 (#211)
- Grok 3: 13.7 (#333)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1434 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 36.1% |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 5.5% |
| Epoch Capabilities Index | — | 138.33 |

## Math

- ERNIE 5.1: 40.3 (#92)
- Grok 3: 38.0 (#145)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Math | 1481 | 1391 |
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| Omni-MATH | — | 46.4% |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- ERNIE 5.1: 41.9 (#102)
- Grok 3: 46.2 (#82)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Expert | 1492 | 1421 |
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 78.8% |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 5.8% |
| GPQA (HELM) | — | 65% |

## Multilingual

- ERNIE 5.1: 55.5 (#29)
- Grok 3: 52.3 (#87)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Non-English | 1454 | 1410 |
| LMArena Chinese | 1508 | 1448 |
| LMArena French | 1488 | 1460 |
| LMArena German | 1470 | 1431 |
| LMArena Japanese | 1422 | 1387 |
| LMArena Korean | 1427 | 1373 |
| LMArena Russian | 1459 | 1416 |
| LMArena Spanish | 1473 | 1417 |

## Instruction Following

- ERNIE 5.1: 76.7 (#37)
- Grok 3: 75.0 (#73)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1409 |
| IFEval | — | 88.4% |

## Long Context

- ERNIE 5.1: 44.7 (#59)
- Grok 3: 38.7 (#192)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1462 | 1439 |
| Fiction.LiveBench | — | 58.3% |

## Writing & Preference

- ERNIE 5.1: 65.1 (#52)
- Grok 3: 55.8 (#141)

| Benchmark | ERNIE 5.1 | Grok 3 |
|---|---|---|
| LMArena Text | 1468 | 1426 |
| LMArena Creative Writing | 1441 | 1414 |
| LMArena Multi-Turn | 1471 | 1425 |
| Short-Story Creative Writing | — | 76.4% |
| EQ-Bench Creative Writing | — | 1186 |
| WildBench | — | 84.9% |

## FAQ

### Is ERNIE 5.1 better than Grok 3?

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 39.9 on the Noometry Index.

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

ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 41.9 in the Noometry coding category.

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

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Grok 3 has 40.