Model comparison
ERNIE 5.1 vs o3-pro
ERNIE 5.1 and o3-pro score almost the same on the Noometry Index (43.8 vs 42.9), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
BaiduSummary
- The widest gap is in long context, where o3-pro leads 72.2 to 44.7.
Side by side
| ERNIE 5.1 | o3-pro | |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.8 | 42.9 |
| Released | — | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 19 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
ERNIE 5.1: 44.0 (#76), o3-pro: 55.5 (#24)
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| LMArena Coding | 1488 | — |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, o3-pro: —
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning o3-pro leads
ERNIE 5.1: 21.9 (#211), o3-pro: 23.8 (#171)
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 59.3% |
| LMArena Hard Prompts | 1481 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.42 |
Math Not comparable
ERNIE 5.1: 40.3 (#92), o3-pro: —
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| LMArena Math | 1481 | — |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), o3-pro: 29.5 (#238)
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1492 | — |
Multilingual Not comparable
ERNIE 5.1: 55.5 (#29), o3-pro: —
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| LMArena Non-English | 1454 | — |
| LMArena Chinese | 1508 | — |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1473 | — |
Instruction Following Not comparable
ERNIE 5.1: 76.7 (#37), o3-pro: —
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1460 | — |
Long Context o3-pro leads
ERNIE 5.1: 44.7 (#59), o3-pro: 72.2 (#1)
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1462 | — |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), o3-pro: 57.1 (#133)
| Benchmark | ERNIE 5.1 | o3-pro |
|---|---|---|
| LMArena Text | 1468 | — |
| LMArena Creative Writing | 1441 | — |
| Short-Story Creative Writing | — | 84.4% |
| LMArena Multi-Turn | 1471 | — |
Frequently asked questions
Is ERNIE 5.1 better than o3-pro?
ERNIE 5.1 and o3-pro score almost the same on the Noometry Index (43.8 vs 42.9), so choose on price, context window or the category you care about most.
Is ERNIE 5.1 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 44.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and o3-pro share?
0 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and o3-pro has 12.