Model comparison
ERNIE 5.1 vs Gemma 2B
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
Baidu
GoogleSummary
- They share 11 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Gemma 2B 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 24.0.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Gemma 2B | |
|---|---|---|
| Provider | Baidu | |
| Noometry Index | 43.8 | 29.6 |
| Released | — | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 23 |
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), Gemma 2B: 29.4 (#305)
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Coding | 1488 | 1010 |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Gemma 2B: —
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Gemma 2B: 18.8 (#275)
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 989 |
| NYT Connections (extended) | 23.4% | — |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 94.2 |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Gemma 2B: 30.0 (#239)
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Math | 1481 | 1009 |
| GSM8K | — | 17.7% |
Knowledge Not comparable
ERNIE 5.1: 41.9 (#102), Gemma 2B: —
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Expert | 1492 | — |
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Gemma 2B: 23.0 (#294)
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1454 | 958 |
| LMArena Chinese | 1508 | 986 |
| LMArena Russian | 1459 | 937 |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Spanish | 1473 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Gemma 2B: 48.5 (#302)
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1460 | 970 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Gemma 2B: 29.9 (#291)
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1462 | 981 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Gemma 2B: 24.0 (#308)
| Benchmark | ERNIE 5.1 | Gemma 2B |
|---|---|---|
| LMArena Text | 1468 | 1002 |
| LMArena Creative Writing | 1441 | 987 |
| LMArena Multi-Turn | 1471 | 945 |
Frequently asked questions
Is ERNIE 5.1 better than Gemma 2B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.6 on the Noometry Index.
Is ERNIE 5.1 or Gemma 2B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 29.4 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Gemma 2B share?
11 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Gemma 2B has 23.