# ERNIE 5.0 0110 vs gpt-oss-20b

> ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 32.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-0-vs-gpt-oss-20b
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 6 categories and gpt-oss-20b in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.1 to 35.5.
- gpt-oss-20b has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 41.8 | 32.5 |
| Rank | 129 | 255 |
| Context | — | 131K |
| Input $/M | — | $0.018 |
| Output $/M | — | $0.09 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.0 0110: 43.0 (#94)
- gpt-oss-20b: 37.6 (#192)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1455 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |

## Agentic & Tool Use

- ERNIE 5.0 0110: —
- gpt-oss-20b: 9.3 (#154)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |

## Reasoning

- ERNIE 5.0 0110: 17.0 (#297)
- gpt-oss-20b: 19.3 (#261)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1445 | 1274 |
| Kagi LLM Benchmark | — | 53.2% |
| NYT Connections (extended) | 10.3% | — |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| Thematic Generalization | 41.7% | — |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.82 |

## Math

- ERNIE 5.0 0110: 39.3 (#110)
- gpt-oss-20b: 39.4 (#103)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1437 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |

## Knowledge

- ERNIE 5.0 0110: 39.8 (#128)
- gpt-oss-20b: 34.6 (#195)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1428 | 1258 |
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |

## Multimodal

- ERNIE 5.0 0110: 39.9 (#53)
- gpt-oss-20b: —

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Vision | 1249 | — |

## Multilingual

- ERNIE 5.0 0110: 54.1 (#49)
- gpt-oss-20b: 42.2 (#197)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1436 | 1268 |
| LMArena Chinese | 1512 | 1314 |
| LMArena German | 1460 | 1255 |
| LMArena Japanese | 1382 | 1244 |
| LMArena Korean | 1406 | 1236 |
| LMArena Russian | 1446 | 1278 |
| LMArena Spanish | 1473 | 1267 |
| LMArena French | 1467 | — |

## Instruction Following

- ERNIE 5.0 0110: 74.5 (#92)
- gpt-oss-20b: 61.8 (#240)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1413 | 1236 |
| IFEval | — | 73.2% |

## Long Context

- ERNIE 5.0 0110: 43.4 (#95)
- gpt-oss-20b: 37.9 (#209)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1422 | 1250 |

## Writing & Preference

- ERNIE 5.0 0110: 63.1 (#66)
- gpt-oss-20b: 35.5 (#265)

| Benchmark | ERNIE 5.0 0110 | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1445 | 1287 |
| LMArena Creative Writing | 1426 | 1201 |
| LMArena Multi-Turn | 1434 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |

## FAQ

### Is ERNIE 5.0 0110 better than gpt-oss-20b?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 32.5 on the Noometry Index.

### Is ERNIE 5.0 0110 or gpt-oss-20b better for coding?

ERNIE 5.0 0110 scores higher on coding benchmarks: 43.0 versus 37.6 in the Noometry coding category.

### How many benchmarks do ERNIE 5.0 0110 and gpt-oss-20b share?

16 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and gpt-oss-20b has 34.