Model comparison
ERNIE 5.1 vs Llama 3-70B
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 28.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
MetaSummary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Llama 3-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where ERNIE 5.1 leads 37.5 to 12.0.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Llama 3-70B | |
|---|---|---|
| Provider | Baidu | Meta |
| Noometry Index | 43.1 | 28.5 |
| Released | — | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 43.4 (#78), Llama 3-70B: 35.3 (#215)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1488 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Llama 3-70B: 20.9 (#132)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 20.9 (#209), Llama 3-70B: 17.4 (#284)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| NYT Connections (extended) | 23.4% | — |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.91 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), Llama 3-70B: 12.0 (#299)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Math | 1481 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.2 (#103), Llama 3-70B: 20.8 (#272)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1491 | 1149 |
| GPQA Diamond | — | 40.6% |
| MMLU | — | 79.3% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.7 (#28), Llama 3-70B: 33.8 (#246)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1455 | 1142 |
| LMArena Chinese | 1507 | 1114 |
| LMArena French | 1486 | 1231 |
| LMArena German | 1470 | 1169 |
| LMArena Japanese | 1422 | 1017 |
| LMArena Korean | 1428 | 1017 |
| LMArena Russian | 1459 | 1159 |
| LMArena Spanish | 1472 | 1241 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.9 (#35), Llama 3-70B: 62.8 (#233)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1194 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#56), Llama 3-70B: 35.6 (#235)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1462 | 1174 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.3 (#50), Llama 3-70B: 43.0 (#225)
| Benchmark | ERNIE 5.1 | Llama 3-70B |
|---|---|---|
| LMArena Text | 1468 | 1221 |
| LMArena Creative Writing | 1440 | 1210 |
| LMArena Multi-Turn | 1471 | 1223 |
Frequently asked questions
Is ERNIE 5.1 better than Llama 3-70B?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 28.5 on the Noometry Index.
Is ERNIE 5.1 or Llama 3-70B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 35.3 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Llama 3-70B share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Llama 3-70B has 31.