Model comparison
ERNIE 5.1 vs Llama 3.1-70B
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 29.4 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 3.1-70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 35.6.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Llama 3.1-70B | |
|---|---|---|
| Provider | Baidu | Meta |
| Noometry Index | 43.1 | 29.4 |
| Released | — | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 19 | 35 |
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 3.1-70B: 29.8 (#292)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 1488 | 1260 |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Llama 3.1-70B: 24.9 (#104)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
| LMArena Search | 1227 | — |
Reasoning Too close to call
ERNIE 5.1: 20.9 (#209), Llama 3.1-70B: 20.8 (#215)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1241 |
| NYT Connections (extended) | 23.4% | — |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| Epoch Capabilities Index | — | 125.91 |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), Llama 3.1-70B: 12.7 (#298)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 1481 | 1252 |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.2 (#103), Llama 3.1-70B: 24.1 (#264)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Expert | 1491 | 1209 |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.7 (#28), Llama 3.1-70B: 38.9 (#220)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1455 | 1219 |
| LMArena Chinese | 1507 | 1215 |
| LMArena French | 1486 | 1260 |
| LMArena German | 1470 | 1222 |
| LMArena Japanese | 1422 | 1132 |
| LMArena Korean | 1428 | 1140 |
| LMArena Russian | 1459 | 1234 |
| LMArena Spanish | 1472 | 1253 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.9 (#35), Llama 3.1-70B: 65.5 (#218)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1231 |
| IFEval | — | 82.1% |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#56), Llama 3.1-70B: 37.6 (#208)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1462 | 1241 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.3 (#50), Llama 3.1-70B: 35.6 (#262)
| Benchmark | ERNIE 5.1 | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1468 | 1261 |
| LMArena Creative Writing | 1440 | 1232 |
| LMArena Multi-Turn | 1471 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
Frequently asked questions
Is ERNIE 5.1 better than Llama 3.1-70B?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 29.4 on the Noometry Index.
Is ERNIE 5.1 or Llama 3.1-70B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 29.8 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Llama 3.1-70B share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Llama 3.1-70B has 35.