Model comparison
ERNIE 5.1 vs GPT-4.1 nano
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 27.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
BaiduSummary
- They share 14 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and GPT-4.1 nano 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 40.5.
Side by side
| ERNIE 5.1 | GPT-4.1 nano | |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.8 | 27.9 |
| Released | — | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.40 |
| 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-4.1 nano: 24.1 (#330)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Coding | 1488 | 1306 |
| Aider Polyglot | — | 8.9% |
| SciCode | — | 25.9% |
| WeirdML | — | 19% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, GPT-4.1 nano: 26.5 (#104)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), GPT-4.1 nano: 8.5 (#349)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1286 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 33.3% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 0% |
| CritPt | — | 0% |
| DTBench | — | 52.5% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 129.62 |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), GPT-4.1 nano: 26.9 (#252)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Math | 1481 | 1274 |
| OTIS Mock AIME 2024-2025 | — | 28.9% |
| Omni-MATH | — | 36.7% |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), GPT-4.1 nano: 21.8 (#273)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Expert | 1492 | 1272 |
| GPQA Diamond | — | 48.9% |
| SimpleQA Verified | — | 6% |
| MMLU-Pro | — | 55% |
| GPQA (HELM) | — | 50.7% |
Multimodal Not comparable
ERNIE 5.1: —, GPT-4.1 nano: 29.2 (#113)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), GPT-4.1 nano: 41.6 (#205)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1454 | 1260 |
| LMArena Chinese | 1508 | 1270 |
| LMArena German | 1470 | 1288 |
| LMArena Japanese | 1422 | 1198 |
| LMArena Russian | 1459 | 1261 |
| LMArena French | 1488 | — |
| LMArena Korean | 1427 | — |
| LMArena Spanish | 1473 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), GPT-4.1 nano: 67.8 (#193)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Instruction Following | 1460 | 1267 |
| IFEval | — | 84.3% |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), GPT-4.1 nano: 23.7 (#296)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Longer Query | 1462 | 1283 |
| Fiction.LiveBench | — | 25% |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), GPT-4.1 nano: 40.5 (#243)
| Benchmark | ERNIE 5.1 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1468 | 1285 |
| LMArena Creative Writing | 1441 | 1260 |
| LMArena Multi-Turn | 1471 | 1277 |
| EQ-Bench Creative Writing | — | 946 |
| WildBench | — | 81.2% |
Frequently asked questions
Is ERNIE 5.1 better than GPT-4.1 nano?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 27.9 on the Noometry Index.
Is ERNIE 5.1 or GPT-4.1 nano better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 24.1 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and GPT-4.1 nano share?
14 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-4.1 nano has 38.