Model comparison
ERNIE 5.1 vs GPT-4
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
BaiduSummary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 34.9.
Side by side
| ERNIE 5.1 | GPT-4 | |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.8 | 29.1 |
| Released | — | 2023-03-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $60 |
| Results tracked | 19 | 38 |
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), GPT-4: 31.6 (#283)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Coding | 1488 | 1254 |
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| HumanEval+ | — | 79.3% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, GPT-4: —
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Search | 1227 | — |
| METR Time Horizons | — | 36.1% |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), GPT-4: 17.8 (#289)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1241 |
| NYT Connections (extended) | 23.4% | — |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| Epoch Capabilities Index | — | 125.89 |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), GPT-4: 10.8 (#309)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Math | 1481 | 1269 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), GPT-4: 18.4 (#282)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Expert | 1492 | 1211 |
| GPQA Diamond | — | 35.7% |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), GPT-4: 40.6 (#215)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Non-English | 1454 | 1246 |
| LMArena Chinese | 1508 | 1242 |
| LMArena French | 1488 | 1283 |
| LMArena German | 1470 | 1251 |
| LMArena Japanese | 1422 | 1209 |
| LMArena Korean | 1427 | 1184 |
| LMArena Russian | 1459 | 1251 |
| LMArena Spanish | 1473 | 1261 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), GPT-4: 65.3 (#222)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1241 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), GPT-4: 37.7 (#212)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1462 | 1244 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), GPT-4: 34.9 (#268)
| Benchmark | ERNIE 5.1 | GPT-4 |
|---|---|---|
| LMArena Text | 1468 | 1263 |
| LMArena Creative Writing | 1441 | 1244 |
| LMArena Multi-Turn | 1471 | 1257 |
| EQ-Bench Creative Writing | — | 752 |
Frequently asked questions
Is ERNIE 5.1 better than GPT-4?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 29.1 on the Noometry Index.
Is ERNIE 5.1 or GPT-4 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 31.6 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and GPT-4 share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-4 has 38.