Model comparison
ERNIE 5.1 vs Qwen2-72B
ERNIE 5.1 is the stronger model overall, scoring 43.8 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 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 40.8.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Qwen2-72B | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.8 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1488 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen2-72B: 17.0 (#146)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| LMArena Search | 1227 | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
ERNIE 5.1: 21.9 (#211), Qwen2-72B: 23.2 (#181)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1191 |
| NYT Connections (extended) | 23.4% | — |
| Epoch Capabilities Index | — | 125.28 |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Qwen2-72B: 30.2 (#236)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1481 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Qwen2-72B: 21.2 (#275)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1492 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Qwen2-72B: 35.9 (#244)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1454 | 1176 |
| LMArena Chinese | 1508 | 1240 |
| LMArena French | 1488 | 1170 |
| LMArena German | 1470 | 1151 |
| LMArena Japanese | 1422 | 1111 |
| LMArena Korean | 1427 | 1083 |
| LMArena Russian | 1459 | 1169 |
| LMArena Spanish | 1473 | 1169 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Qwen2-72B: 61.7 (#241)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1181 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Qwen2-72B: 36.1 (#235)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1462 | 1192 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Qwen2-72B: 40.8 (#241)
| Benchmark | ERNIE 5.1 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1468 | 1203 |
| LMArena Creative Writing | 1441 | 1181 |
| LMArena Multi-Turn | 1471 | 1196 |
Frequently asked questions
Is ERNIE 5.1 better than Qwen2-72B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 30.0 on the Noometry Index.
Is ERNIE 5.1 or Qwen2-72B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 29.1 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Qwen2-72B share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen2-72B has 26.