Model comparison
DeepSeek LLM 67B vs ERNIE 5.0 0110
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
BaiduSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and ERNIE 5.0 0110 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where ERNIE 5.0 0110 leads 39.8 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | ERNIE 5.0 0110 | |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 24.9 | 41.8 |
| Released | 2023-11-29 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.0 0110 leads
DeepSeek LLM 67B: 31.9 (#278), ERNIE 5.0 0110: 43.0 (#94)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Coding | 1096 | 1455 |
Reasoning Too close to call
DeepSeek LLM 67B: 16.5 (#304), ERNIE 5.0 0110: 17.0 (#297)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1445 |
| NYT Connections (extended) | — | 10.3% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.7% |
| Epoch Capabilities Index | 110.5 | — |
Math ERNIE 5.0 0110 leads
DeepSeek LLM 67B: 8.7 (#324), ERNIE 5.0 0110: 39.3 (#110)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Math | 1108 | 1437 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge ERNIE 5.0 0110 leads
DeepSeek LLM 67B: 7.0 (#313), ERNIE 5.0 0110: 39.8 (#128)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1428 |
Multimodal Not comparable
DeepSeek LLM 67B: —, ERNIE 5.0 0110: 39.9 (#53)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Vision | — | 1249 |
Multilingual ERNIE 5.0 0110 leads
DeepSeek LLM 67B: 29.4 (#267), ERNIE 5.0 0110: 54.1 (#49)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Non-English | 1073 | 1436 |
| LMArena Chinese | 1132 | 1512 |
| LMArena French | — | 1467 |
| LMArena German | — | 1460 |
| LMArena Japanese | — | 1382 |
| LMArena Korean | — | 1406 |
| LMArena Russian | — | 1446 |
| LMArena Spanish | — | 1473 |
Instruction Following ERNIE 5.0 0110 leads
DeepSeek LLM 67B: 55.4 (#277), ERNIE 5.0 0110: 74.5 (#92)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1413 |
Long Context ERNIE 5.0 0110 leads
DeepSeek LLM 67B: 33.1 (#265), ERNIE 5.0 0110: 43.4 (#95)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Longer Query | 1092 | 1422 |
Writing & Preference ERNIE 5.0 0110 leads
DeepSeek LLM 67B: 31.6 (#282), ERNIE 5.0 0110: 63.1 (#66)
| Benchmark | DeepSeek LLM 67B | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Text | 1105 | 1445 |
| LMArena Creative Writing | 1067 | 1426 |
| LMArena Multi-Turn | 1082 | 1434 |
Frequently asked questions
Is DeepSeek LLM 67B better than ERNIE 5.0 0110?
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or ERNIE 5.0 0110 better for coding?
ERNIE 5.0 0110 scores higher on coding benchmarks: 43.0 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and ERNIE 5.0 0110 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and ERNIE 5.0 0110 has 20.