Model comparison
ERNIE 5.1 vs Qwen1.5-32B
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Qwen1.5-32B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 34.4.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Qwen1.5-32B | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.1 | 30.0 |
| Released | — | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 43.4 (#78), Qwen1.5-32B: 31.1 (#278)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1488 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen1.5-32B: —
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Too close to call
ERNIE 5.1: 20.9 (#209), Qwen1.5-32B: 20.9 (#210)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1131 |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), Qwen1.5-32B: 30.5 (#207)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1481 | 1155 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.2 (#103), Qwen1.5-32B: 13.5 (#291)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1491 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.7 (#28), Qwen1.5-32B: 31.6 (#254)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1455 | 1106 |
| LMArena Chinese | 1507 | 1176 |
| LMArena French | 1486 | 1100 |
| LMArena German | 1470 | 1058 |
| LMArena Japanese | 1422 | 1027 |
| LMArena Korean | 1428 | 1007 |
| LMArena Russian | 1459 | 1073 |
| LMArena Spanish | 1472 | 1089 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.9 (#35), Qwen1.5-32B: 58.0 (#260)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1116 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#56), Qwen1.5-32B: 34.7 (#241)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1462 | 1146 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.3 (#50), Qwen1.5-32B: 34.4 (#266)
| Benchmark | ERNIE 5.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1468 | 1137 |
| LMArena Creative Writing | 1440 | 1083 |
| LMArena Multi-Turn | 1471 | 1140 |
Frequently asked questions
Is ERNIE 5.1 better than Qwen1.5-32B?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.
Is ERNIE 5.1 or Qwen1.5-32B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 31.1 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Qwen1.5-32B share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen1.5-32B has 21.