Model comparison
ERNIE 5.1 vs Llama 2-13B
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.6 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 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 29.8.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Llama 2-13B | |
|---|---|---|
| Provider | Baidu | Meta |
| Noometry Index | 43.8 | 29.6 |
| Released | — | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 32 |
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 2-13B: 30.9 (#291)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1488 | 1062 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Llama 2-13B: —
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Llama 2-13B: 12.8 (#337)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1051 |
| NYT Connections (extended) | 23.4% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 106.17 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Llama 2-13B: 31.1 (#229)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1481 | 1065 |
| GSM8K | — | 36.9% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Llama 2-13B: 28.1 (#249)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1492 | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
ERNIE 5.1: —, Llama 2-13B: —
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Llama 2-13B: 26.5 (#279)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1454 | 1024 |
| LMArena Chinese | 1508 | 1001 |
| LMArena French | 1488 | 1044 |
| LMArena German | 1470 | 1009 |
| LMArena Japanese | 1422 | 894 |
| LMArena Korean | 1427 | 953 |
| LMArena Russian | 1459 | 1055 |
| LMArena Spanish | 1473 | 1087 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Llama 2-13B: 53.3 (#287)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1045 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Llama 2-13B: 32.3 (#269)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1462 | 1064 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Llama 2-13B: 29.8 (#289)
| Benchmark | ERNIE 5.1 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1468 | 1084 |
| LMArena Creative Writing | 1441 | 1047 |
| LMArena Multi-Turn | 1471 | 1050 |
Frequently asked questions
Is ERNIE 5.1 better than Llama 2-13B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.6 on the Noometry Index.
Is ERNIE 5.1 or Llama 2-13B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 30.9 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Llama 2-13B share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Llama 2-13B has 32.