Model comparison
ERNIE 5.1 vs o1
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 40.6 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 4 categories and o1 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 55.8.
Side by side
| ERNIE 5.1 | o1 | |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.1 | 40.6 |
| Released | — | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $60 |
| Results tracked | 19 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
ERNIE 5.1: 43.4 (#78), o1: 45.7 (#64)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Coding | 1488 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, o1: 24.3 (#111)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| Cybench | — | 10% |
| LMArena Search | 1227 | — |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
ERNIE 5.1: 20.9 (#209), o1: 27.5 (#103)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1372 |
| SimpleBench | — | 41.7% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.92 |
| LiveBench | — | 75.7% |
Math ERNIE 5.1 leads
ERNIE 5.1: 37.5 (#96), o1: 34.9 (#150)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Math | 1481 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge Too close to call
ERNIE 5.1: 41.2 (#103), o1: 41.5 (#101)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Expert | 1491 | 1362 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
Multimodal Not comparable
ERNIE 5.1: —, o1: 33.6 (#87)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.7 (#28), o1: 48.8 (#137)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Non-English | 1455 | 1359 |
| LMArena Chinese | 1507 | 1394 |
| LMArena French | 1486 | 1343 |
| LMArena German | 1470 | 1337 |
| LMArena Japanese | 1422 | 1346 |
| LMArena Korean | 1428 | 1396 |
| LMArena Russian | 1459 | 1356 |
| LMArena Spanish | 1472 | 1345 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.9 (#35), o1: 75.0 (#82)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1368 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
ERNIE 5.1: 44.7 (#56), o1: 50.3 (#9)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Longer Query | 1462 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.3 (#50), o1: 55.8 (#139)
| Benchmark | ERNIE 5.1 | o1 |
|---|---|---|
| LMArena Text | 1468 | 1366 |
| LMArena Creative Writing | 1440 | 1347 |
| LMArena Multi-Turn | 1471 | 1368 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is ERNIE 5.1 better than o1?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 40.6 on the Noometry Index.
Is ERNIE 5.1 or o1 better for coding?
o1 scores higher on coding benchmarks: 45.7 versus 43.4 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and o1 share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and o1 has 52.