# ERNIE 5.1 vs Granite 3.0 2b Instruct

> ERNIE 5.1 is the stronger model overall, scoring 43.8 to 30.8 on the Noometry Index.

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

## Summary

- They share 12 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Granite 3.0 2b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 29.6.
- Granite 3.0 2b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| Provider | Baidu | IBM |
| Noometry Index | 43.8 | 30.8 |
| Rank | 83 | 286 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 44.0 (#76)
- Granite 3.0 2b Instruct: 28.3 (#316)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Coding | 1488 | 1090 |
| BigCodeBench Instruct | — | 20.5% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Granite 3.0 2b Instruct: —

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 21.9 (#211)
- Granite 3.0 2b Instruct: 20.5 (#235)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1073 |
| NYT Connections (extended) | 23.4% | — |

## Math

- ERNIE 5.1: 40.3 (#92)
- Granite 3.0 2b Instruct: 32.2 (#217)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | 1481 | 1117 |

## Knowledge

- ERNIE 5.1: 41.9 (#102)
- Granite 3.0 2b Instruct: 29.0 (#241)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | 1492 | 1064 |

## Multilingual

- ERNIE 5.1: 55.5 (#29)
- Granite 3.0 2b Instruct: 27.0 (#278)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | 1454 | 1033 |
| LMArena Chinese | 1508 | 1070 |
| LMArena Russian | 1459 | 1045 |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Spanish | 1473 | — |

## Instruction Following

- ERNIE 5.1: 76.7 (#37)
- Granite 3.0 2b Instruct: 53.9 (#284)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1460 | 1056 |

## Long Context

- ERNIE 5.1: 44.7 (#59)
- Granite 3.0 2b Instruct: 32.5 (#268)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1462 | 1070 |

## Writing & Preference

- ERNIE 5.1: 65.1 (#52)
- Granite 3.0 2b Instruct: 29.6 (#292)

| Benchmark | ERNIE 5.1 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | 1468 | 1080 |
| LMArena Creative Writing | 1441 | 1046 |
| LMArena Multi-Turn | 1471 | 1053 |

## FAQ

### Is ERNIE 5.1 better than Granite 3.0 2b Instruct?

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 30.8 on the Noometry Index.

### Is ERNIE 5.1 or Granite 3.0 2b Instruct better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 28.3 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Granite 3.0 2b Instruct share?

12 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Granite 3.0 2b Instruct has 13.