# ERNIE 5.1 vs Gemma 4 31B IT

> ERNIE 5.1 and Gemma 4 31B IT score almost the same on the Noometry Index (43.1 vs 43.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-gemma-4-31b-it
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. ERNIE 5.1 scores higher in 6 categories and Gemma 4 31B IT in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 4 31B IT leads 26.4 to 20.9.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 70.6% for Gemma 4 31B IT.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| Provider | Baidu | Google |
| Noometry Index | 43.1 | 43.2 |
| Rank | 87 | 85 |
| Context | — | 262K |
| Input $/M | — | $0.09 |
| Output $/M | — | $0.34 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 43.4 (#78)
- Gemma 4 31B IT: 41.9 (#98)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Coding | 1488 | 1459 |
| LMArena WebDev | — | 1364 |
| SciCode | — | 43.4% |
| WeirdML | — | 52.3% |
| ALE-Bench | — | 925.5 |

## Agentic & Tool Use

- ERNIE 5.1: —
- Gemma 4 31B IT: —

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- Gemma 4 31B IT: 26.4 (#119)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| NYT Connections (extended) | 23.4% | 70.6% |
| LMArena Hard Prompts | 1481 | 1448 |
| Kagi LLM Benchmark | — | 63.5% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| Thematic Generalization | — | 53% |
| DTBench | — | 82.7% |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| Epoch Capabilities Index | — | 142.74 |

## Math

- ERNIE 5.1: 37.5 (#96)
- Gemma 4 31B IT: 41.3 (#72)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Math | 1481 | 1464 |
| OTIS Mock AIME 2024-2025 | — | 73.3% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- Gemma 4 31B IT: 37.9 (#141)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Expert | 1491 | 1465 |
| GPQA Diamond | — | 75.8% |
| SimpleQA Verified | — | 10.4% |
| Vectara Hallucination Rate | — | 7.4% |

## Multimodal

- ERNIE 5.1: —
- Gemma 4 31B IT: 41.0 (#32)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1278 |
| LMArena Document | — | 1425 |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- Gemma 4 31B IT: 54.0 (#52)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1455 | 1431 |
| LMArena Chinese | 1507 | 1478 |
| LMArena French | 1486 | 1436 |
| LMArena Russian | 1459 | 1462 |
| LMArena Spanish | 1472 | 1443 |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1428 | — |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- Gemma 4 31B IT: 75.6 (#58)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1460 | 1433 |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- Gemma 4 31B IT: 44.2 (#67)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1462 | 1446 |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- Gemma 4 31B IT: 60.7 (#92)

| Benchmark | ERNIE 5.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1468 | 1443 |
| LMArena Creative Writing | 1440 | 1416 |
| LMArena Multi-Turn | 1471 | 1452 |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |

## FAQ

### Is ERNIE 5.1 better than Gemma 4 31B IT?

ERNIE 5.1 and Gemma 4 31B IT score almost the same on the Noometry Index (43.1 vs 43.2), so choose on price, context window or the category you care about most.

### Is ERNIE 5.1 or Gemma 4 31B IT better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 41.9 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Gemma 4 31B IT share?

15 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Gemma 4 31B IT has 35.