Model comparison
ERNIE 5.1 vs Llama2 70b Steerlm Chat
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
Baidu
NVIDIASummary
- They share 9 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Llama2 70b Steerlm Chat in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 31.6.
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Baidu | NVIDIA |
| Noometry Index | 43.8 | 31.8 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 9 |
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), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1488 | 1025 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Llama2 70b Steerlm Chat: —
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1047 |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1481 | 1072 |
Knowledge Not comparable
ERNIE 5.1: 41.9 (#102), Llama2 70b Steerlm Chat: —
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Expert | 1492 | — |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1454 | 1063 |
| 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), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1460 | 1060 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1462 | 998 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | ERNIE 5.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1468 | 1098 |
| LMArena Creative Writing | 1441 | 1091 |
| LMArena Multi-Turn | 1471 | 1058 |
Frequently asked questions
Is ERNIE 5.1 better than Llama2 70b Steerlm Chat?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.8 on the Noometry Index.
Is ERNIE 5.1 or Llama2 70b Steerlm Chat better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 29.9 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Llama2 70b Steerlm Chat has 9.