Model comparison
ERNIE 5.1 vs Qwen1.5-110B
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 34.2 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 Qwen1.5-110B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 38.0.
- Qwen1.5-110B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Qwen1.5-110B | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.8 | 34.2 |
| Released | — | 2024-04-25 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 20 |
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), Qwen1.5-110B: 33.0 (#264)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1488 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen1.5-110B: —
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Too close to call
ERNIE 5.1: 21.9 (#211), Qwen1.5-110B: 22.7 (#189)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1168 |
| NYT Connections (extended) | 23.4% | — |
| ForecastBench | — | 57.7 |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Qwen1.5-110B: 33.7 (#201)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1481 | 1185 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Qwen1.5-110B: 31.2 (#219)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1492 | 1144 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Qwen1.5-110B: 33.6 (#250)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1454 | 1142 |
| LMArena Chinese | 1508 | 1206 |
| LMArena French | 1488 | 1151 |
| LMArena German | 1470 | 1123 |
| LMArena Japanese | 1422 | 1074 |
| LMArena Korean | 1427 | 1044 |
| LMArena Russian | 1459 | 1118 |
| LMArena Spanish | 1473 | 1142 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Qwen1.5-110B: 60.3 (#252)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1158 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Qwen1.5-110B: 35.1 (#242)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1462 | 1157 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Qwen1.5-110B: 38.0 (#255)
| Benchmark | ERNIE 5.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1468 | 1175 |
| LMArena Creative Writing | 1441 | 1148 |
| LMArena Multi-Turn | 1471 | 1160 |
Frequently asked questions
Is ERNIE 5.1 better than Qwen1.5-110B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 34.2 on the Noometry Index.
Is ERNIE 5.1 or Qwen1.5-110B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 33.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Qwen1.5-110B share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen1.5-110B has 20.