Model comparison
ERNIE 5.0 0110 vs Qwen1.5-14B
ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 32.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
Baidu
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 7 categories and Qwen1.5-14B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.4 to 33.7.
- Qwen1.5-14B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.0 0110 | Qwen1.5-14B | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 41.2 | 32.1 |
| Released | — | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 20 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 42.3 (#94), Qwen1.5-14B: 32.5 (#259)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1455 | 1138 |
Reasoning Qwen1.5-14B leads
ERNIE 5.0 0110: 16.3 (#296), Qwen1.5-14B: 20.5 (#217)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1446 | 1113 |
| NYT Connections (extended) | 10.3% | — |
| Thematic Generalization | 41.7% | — |
Math ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 36.5 (#111), Qwen1.5-14B: 29.9 (#214)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1437 | 1125 |
Knowledge ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 39.2 (#125), Qwen1.5-14B: 29.3 (#230)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1427 | 1094 |
| MMLU | — | 68.6% |
Multimodal Not comparable
ERNIE 5.0 0110: 39.1 (#49), Qwen1.5-14B: —
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Vision | 1248 | — |
Multilingual ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 54.3 (#47), Qwen1.5-14B: 30.8 (#257)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1436 | 1095 |
| LMArena Chinese | 1512 | 1147 |
| LMArena French | 1466 | 1115 |
| LMArena German | 1462 | 1043 |
| LMArena Japanese | 1383 | 1019 |
| LMArena Russian | 1446 | 1046 |
| LMArena Spanish | 1473 | 1085 |
| LMArena Korean | 1406 | — |
Instruction Following ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 74.7 (#88), Qwen1.5-14B: 57.1 (#266)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1413 | 1102 |
Long Context ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 43.4 (#90), Qwen1.5-14B: 33.7 (#252)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1422 | 1113 |
Writing & Preference ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 63.4 (#64), Qwen1.5-14B: 33.7 (#270)
| Benchmark | ERNIE 5.0 0110 | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1445 | 1128 |
| LMArena Creative Writing | 1426 | 1091 |
| LMArena Multi-Turn | 1433 | 1110 |
Frequently asked questions
Is ERNIE 5.0 0110 better than Qwen1.5-14B?
ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 32.1 on the Noometry Index.
Is ERNIE 5.0 0110 or Qwen1.5-14B better for coding?
ERNIE 5.0 0110 scores higher on coding benchmarks: 42.3 versus 32.5 in the Noometry coding category.
How many benchmarks do ERNIE 5.0 0110 and Qwen1.5-14B share?
16 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Qwen1.5-14B has 17.