Model comparison
ERNIE 5.1 vs Nemotron 4 340b Instruct
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 35.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
NVIDIASummary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Nemotron 4 340b Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 42.9.
- Nemotron 4 340b Instruct has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | Baidu | NVIDIA |
| Noometry Index | 43.1 | 35.3 |
| Released | — | 2024-06-14 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 17 |
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), Nemotron 4 340b Instruct: 34.6 (#223)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1488 | 1209 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Nemotron 4 340b Instruct: —
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Nemotron 4 340b Instruct leads
ERNIE 5.1: 20.9 (#209), Nemotron 4 340b Instruct: 22.4 (#180)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1202 |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), Nemotron 4 340b Instruct: 31.7 (#193)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1481 | 1216 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.2 (#103), Nemotron 4 340b Instruct: 31.4 (#212)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1491 | 1171 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.7 (#28), Nemotron 4 340b Instruct: 38.0 (#228)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1455 | 1206 |
| LMArena Chinese | 1507 | 1214 |
| LMArena French | 1486 | 1196 |
| LMArena German | 1470 | 1192 |
| LMArena Japanese | 1422 | 1128 |
| LMArena Korean | 1428 | 1148 |
| LMArena Russian | 1459 | 1219 |
| LMArena Spanish | 1472 | 1195 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.9 (#35), Nemotron 4 340b Instruct: 63.3 (#227)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1460 | 1203 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#56), Nemotron 4 340b Instruct: 37.1 (#216)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1462 | 1225 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.3 (#50), Nemotron 4 340b Instruct: 42.9 (#229)
| Benchmark | ERNIE 5.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1468 | 1225 |
| LMArena Creative Writing | 1440 | 1203 |
| LMArena Multi-Turn | 1471 | 1214 |
Frequently asked questions
Is ERNIE 5.1 better than Nemotron 4 340b Instruct?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 35.3 on the Noometry Index.
Is ERNIE 5.1 or Nemotron 4 340b Instruct better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 34.6 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Nemotron 4 340b Instruct share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Nemotron 4 340b Instruct has 17.