Model comparison
ERNIE 5.1 vs phi-3-medium 14B
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Baidu
MicrosoftSummary
- The widest gap is in knowledge, where ERNIE 5.1 leads 41.2 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | phi-3-medium 14B | |
|---|---|---|
| Provider | Baidu | Microsoft |
| Noometry Index | 43.1 | 29.1 |
| Released | — | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 13 |
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), phi-3-medium 14B: 36.3 (#198)
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1488 | — |
| BigCodeBench Complete | — | 48.7% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, phi-3-medium 14B: —
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Not comparable
ERNIE 5.1: 20.9 (#209), phi-3-medium 14B: —
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| NYT Connections (extended) | 23.4% | — |
| LMArena Hard Prompts | 1481 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), phi-3-medium 14B: 25.2 (#249)
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1481 | — |
| MATH Level 5 | — | 17.6% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.2 (#103), phi-3-medium 14B: 9.1 (#301)
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1491 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
ERNIE 5.1: 55.7 (#28), phi-3-medium 14B: —
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1455 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1486 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1428 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1472 | — |
Instruction Following Not comparable
ERNIE 5.1: 76.9 (#35), phi-3-medium 14B: —
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1460 | — |
Long Context Not comparable
ERNIE 5.1: 44.7 (#56), phi-3-medium 14B: —
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1462 | — |
Writing & Preference Not comparable
ERNIE 5.1: 65.3 (#50), phi-3-medium 14B: —
| Benchmark | ERNIE 5.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1468 | — |
| LMArena Creative Writing | 1440 | — |
| LMArena Multi-Turn | 1471 | — |
Frequently asked questions
Is ERNIE 5.1 better than phi-3-medium 14B?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.
Is ERNIE 5.1 or phi-3-medium 14B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 36.3 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and phi-3-medium 14B share?
0 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and phi-3-medium 14B has 13.