Model comparison
ERNIE 5.1 vs Llama 13b
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Baidu
MetaSummary
- They share 8 benchmarks with published results for both. ERNIE 5.1 scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 13.8.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Llama 13b | |
|---|---|---|
| Provider | Baidu | Meta |
| Noometry Index | 43.8 | 24.4 |
| Released | — | 2023-02-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 44.0 (#76), Llama 13b: 21.4 (#337)
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Coding | 1488 | 683 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Llama 13b: —
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Llama 13b: 14.0 (#329)
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1481 | 728 |
| NYT Connections (extended) | 23.4% | — |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Llama 13b: 26.7 (#256)
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Math | 1481 | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
ERNIE 5.1: 41.9 (#102), Llama 13b: —
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Expert | 1492 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
ERNIE 5.1: —, Llama 13b: —
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Llama 13b: 16.6 (#297)
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Non-English | 1454 | 819 |
| LMArena Chinese | 1508 | — |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1473 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Llama 13b: 36.7 (#305)
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1460 | 781 |
Long Context Not comparable
ERNIE 5.1: 44.7 (#59), Llama 13b: —
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1462 | — |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Llama 13b: 13.8 (#312)
| Benchmark | ERNIE 5.1 | Llama 13b |
|---|---|---|
| LMArena Text | 1468 | 834 |
| LMArena Creative Writing | 1441 | 794 |
| LMArena Multi-Turn | 1471 | 753 |
Frequently asked questions
Is ERNIE 5.1 better than Llama 13b?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 24.4 on the Noometry Index.
Is ERNIE 5.1 or Llama 13b better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 21.4 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Llama 13b share?
8 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Llama 13b has 21.