Model comparison
ERNIE 5.1 vs Qwen-14B
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Baidu
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Qwen-14B 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 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Qwen-14B | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.8 | 31.4 |
| Released | — | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 18 |
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), Qwen-14B: 31.2 (#288)
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1488 | 1071 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen-14B: —
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Qwen-14B: 19.6 (#257)
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1027 |
| NYT Connections (extended) | 23.4% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Qwen-14B: 31.2 (#227)
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Math | 1481 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
ERNIE 5.1: 41.9 (#102), Qwen-14B: —
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Expert | 1492 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Qwen-14B: 27.5 (#275)
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1454 | 1041 |
| LMArena Chinese | 1508 | 1077 |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1473 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Qwen-14B: 52.4 (#289)
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1031 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Qwen-14B: 31.3 (#280)
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1462 | 1028 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Qwen-14B: 27.6 (#299)
| Benchmark | ERNIE 5.1 | Qwen-14B |
|---|---|---|
| LMArena Text | 1468 | 1051 |
| LMArena Creative Writing | 1441 | 1028 |
| LMArena Multi-Turn | 1471 | 1022 |
Frequently asked questions
Is ERNIE 5.1 better than Qwen-14B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.4 on the Noometry Index.
Is ERNIE 5.1 or Qwen-14B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 31.2 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Qwen-14B share?
10 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen-14B has 18.