Model comparison
Deepseek Coder v2 vs ERNIE 5.0 0110
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
BaiduSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and ERNIE 5.0 0110 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.1 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | ERNIE 5.0 0110 | |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 35.9 | 41.8 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.0 0110 leads
Deepseek Coder v2: 38.1 (#183), ERNIE 5.0 0110: 43.0 (#94)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Coding | 1251 | 1455 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), ERNIE 5.0 0110: 17.0 (#297)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1445 |
| NYT Connections (extended) | — | 10.3% |
| Thematic Generalization | — | 41.7% |
| WinoGrande | 83.7% | — |
Math ERNIE 5.0 0110 leads
Deepseek Coder v2: 34.9 (#190), ERNIE 5.0 0110: 39.3 (#110)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Math | 1241 | 1437 |
| GSM8K | 94.5% | — |
Knowledge ERNIE 5.0 0110 leads
Deepseek Coder v2: 32.3 (#212), ERNIE 5.0 0110: 39.8 (#128)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Expert | 1181 | 1428 |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, ERNIE 5.0 0110: 39.9 (#53)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Vision | — | 1249 |
Multilingual ERNIE 5.0 0110 leads
Deepseek Coder v2: 36.3 (#240), ERNIE 5.0 0110: 54.1 (#49)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Non-English | 1182 | 1436 |
| LMArena Chinese | 1201 | 1512 |
| LMArena French | 1185 | 1467 |
| LMArena German | 1164 | 1460 |
| LMArena Japanese | 1126 | 1382 |
| LMArena Korean | 1104 | 1406 |
| LMArena Russian | 1188 | 1446 |
| LMArena Spanish | 1153 | 1473 |
Instruction Following ERNIE 5.0 0110 leads
Deepseek Coder v2: 61.7 (#242), ERNIE 5.0 0110: 74.5 (#92)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1413 |
Long Context ERNIE 5.0 0110 leads
Deepseek Coder v2: 37.0 (#224), ERNIE 5.0 0110: 43.4 (#95)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Longer Query | 1219 | 1422 |
Writing & Preference ERNIE 5.0 0110 leads
Deepseek Coder v2: 38.2 (#253), ERNIE 5.0 0110: 63.1 (#66)
| Benchmark | Deepseek Coder v2 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Text | 1191 | 1445 |
| LMArena Creative Writing | 1120 | 1426 |
| LMArena Multi-Turn | 1177 | 1434 |
Frequently asked questions
Is Deepseek Coder v2 better than ERNIE 5.0 0110?
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or ERNIE 5.0 0110 better for coding?
ERNIE 5.0 0110 scores higher on coding benchmarks: 43.0 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and ERNIE 5.0 0110 share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and ERNIE 5.0 0110 has 20.