Model comparison
ERNIE 5.1 vs Wizardlm 70b
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Baidu
MicrosoftSummary
- They share 12 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Wizardlm 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 34.9.
- Wizardlm 70b has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Wizardlm 70b | |
|---|---|---|
| Provider | Baidu | Microsoft |
| Noometry Index | 43.1 | 32.4 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 12 |
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), Wizardlm 70b: 30.9 (#280)
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1488 | 1081 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Wizardlm 70b: —
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 20.9 (#209), Wizardlm 70b: 19.8 (#231)
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1079 |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), Wizardlm 70b: 29.7 (#216)
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1481 | 1116 |
Knowledge Not comparable
ERNIE 5.1: 41.2 (#103), Wizardlm 70b: —
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1491 | — |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.7 (#28), Wizardlm 70b: 29.8 (#260)
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1455 | 1078 |
| LMArena Chinese | 1507 | 1052 |
| LMArena German | 1470 | 1083 |
| LMArena Russian | 1459 | 1155 |
| LMArena French | 1486 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1428 | — |
| LMArena Spanish | 1472 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.9 (#35), Wizardlm 70b: 56.5 (#268)
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1460 | 1093 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#56), Wizardlm 70b: 33.3 (#258)
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1462 | 1097 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.3 (#50), Wizardlm 70b: 34.9 (#264)
| Benchmark | ERNIE 5.1 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1468 | 1120 |
| LMArena Creative Writing | 1440 | 1149 |
| LMArena Multi-Turn | 1471 | 1108 |
Frequently asked questions
Is ERNIE 5.1 better than Wizardlm 70b?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 32.4 on the Noometry Index.
Is ERNIE 5.1 or Wizardlm 70b better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 30.9 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Wizardlm 70b share?
12 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Wizardlm 70b has 12.