Model comparison
ERNIE 5.1 vs gpt-oss-20b
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 32.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
BaiduSummary
- They share 16 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and gpt-oss-20b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 35.5.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | gpt-oss-20b | |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.8 | 32.5 |
| Released | — | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 19 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 44.0 (#76), gpt-oss-20b: 37.6 (#192)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1488 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), gpt-oss-20b: 19.3 (#261)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1274 |
| Kagi LLM Benchmark | — | 53.2% |
| NYT Connections (extended) | 23.4% | — |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.82 |
Math Too close to call
ERNIE 5.1: 40.3 (#92), gpt-oss-20b: 39.4 (#103)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1481 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), gpt-oss-20b: 34.6 (#195)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1492 | 1258 |
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), gpt-oss-20b: 42.2 (#197)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1454 | 1268 |
| LMArena Chinese | 1508 | 1314 |
| LMArena German | 1470 | 1255 |
| LMArena Japanese | 1422 | 1244 |
| LMArena Korean | 1427 | 1236 |
| LMArena Russian | 1459 | 1278 |
| LMArena Spanish | 1473 | 1267 |
| LMArena French | 1488 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), gpt-oss-20b: 61.8 (#240)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1460 | 1236 |
| IFEval | — | 73.2% |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), gpt-oss-20b: 37.9 (#209)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1462 | 1250 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), gpt-oss-20b: 35.5 (#265)
| Benchmark | ERNIE 5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1468 | 1287 |
| LMArena Creative Writing | 1441 | 1201 |
| LMArena Multi-Turn | 1471 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is ERNIE 5.1 better than gpt-oss-20b?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 32.5 on the Noometry Index.
Is ERNIE 5.1 or gpt-oss-20b better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 37.6 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and gpt-oss-20b share?
16 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and gpt-oss-20b has 34.