Model comparison
ERNIE 5.1 vs Gemini 1.0 Pro
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 27.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
Baidu
GoogleSummary
- They share 16 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Gemini 1.0 Pro in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 36.2.
Side by side
| ERNIE 5.1 | Gemini 1.0 Pro | |
|---|---|---|
| Provider | Baidu | |
| Noometry Index | 43.1 | 27.1 |
| Released | — | 2023-12-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 24 |
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), Gemini 1.0 Pro: 31.6 (#270)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1488 | 1108 |
| HumanEval+ | — | 55.5% |
| MBPP+ | — | 61.4% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Gemini 1.0 Pro: —
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 20.9 (#209), Gemini 1.0 Pro: 16.4 (#292)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1109 |
| NYT Connections (extended) | 23.4% | — |
| DTBench | — | 45.9% |
| Epoch Capabilities Index | — | 116.97 |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), Gemini 1.0 Pro: 8.7 (#315)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Math | 1481 | 1132 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 11.2% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.2 (#103), Gemini 1.0 Pro: 15.5 (#286)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Expert | 1491 | 1059 |
| GPQA Diamond | — | 34% |
| MMLU | — | 70% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.7 (#28), Gemini 1.0 Pro: 33.5 (#247)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1455 | 1138 |
| LMArena Chinese | 1507 | 1124 |
| LMArena French | 1486 | 1144 |
| LMArena German | 1470 | 1125 |
| LMArena Japanese | 1422 | 1023 |
| LMArena Russian | 1459 | 1186 |
| LMArena Spanish | 1472 | 1118 |
| LMArena Korean | 1428 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.9 (#35), Gemini 1.0 Pro: 57.9 (#262)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1460 | 1114 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#56), Gemini 1.0 Pro: 34.3 (#244)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1462 | 1132 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.3 (#50), Gemini 1.0 Pro: 36.2 (#259)
| Benchmark | ERNIE 5.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1468 | 1149 |
| LMArena Creative Writing | 1440 | 1130 |
| LMArena Multi-Turn | 1471 | 1139 |
Frequently asked questions
Is ERNIE 5.1 better than Gemini 1.0 Pro?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 27.1 on the Noometry Index.
Is ERNIE 5.1 or Gemini 1.0 Pro better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 31.6 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Gemini 1.0 Pro share?
16 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Gemini 1.0 Pro has 24.