Model comparison
ERNIE 5.1 vs GPT-5.4 nano
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 41.9 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 5 categories and GPT-5.4 nano in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 55.7.
Side by side
| ERNIE 5.1 | GPT-5.4 nano | |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.8 | 41.9 |
| Released | — | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.25 |
| Results tracked | 19 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
ERNIE 5.1: 44.0 (#76), GPT-5.4 nano: 43.6 (#84)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Coding | 1488 | 1405 |
| SciCode | — | 46.9% |
| WeirdML | — | 49.2% |
| ALE-Bench | — | 1,005 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, GPT-5.4 nano: —
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning GPT-5.4 nano leads
ERNIE 5.1: 21.9 (#211), GPT-5.4 nano: 23.7 (#173)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1381 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 145.81 |
| ForecastBench | — | 57.3 |
Math Too close to call
ERNIE 5.1: 40.3 (#92), GPT-5.4 nano: 40.9 (#88)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Math | 1481 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 5% |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Too close to call
ERNIE 5.1: 41.9 (#102), GPT-5.4 nano: 41.9 (#103)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Expert | 1492 | 1396 |
| GPQA Diamond | — | 78.5% |
| SimpleQA Verified | — | 11.7% |
| Vectara Hallucination Rate | — | 3.1% |
Multimodal Not comparable
ERNIE 5.1: —, GPT-5.4 nano: 36.7 (#78)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | — | 1196 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), GPT-5.4 nano: 48.6 (#140)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1454 | 1359 |
| LMArena Chinese | 1508 | 1392 |
| LMArena French | 1488 | 1396 |
| LMArena German | 1470 | 1367 |
| LMArena Japanese | 1422 | 1343 |
| LMArena Korean | 1427 | 1320 |
| LMArena Russian | 1459 | 1363 |
| LMArena Spanish | 1473 | 1371 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), GPT-5.4 nano: 71.9 (#144)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1460 | 1362 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), GPT-5.4 nano: 41.6 (#137)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1462 | 1366 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), GPT-5.4 nano: 55.7 (#142)
| Benchmark | ERNIE 5.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1468 | 1372 |
| LMArena Creative Writing | 1441 | 1314 |
| LMArena Multi-Turn | 1471 | 1382 |
Frequently asked questions
Is ERNIE 5.1 better than GPT-5.4 nano?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 41.9 on the Noometry Index.
Is ERNIE 5.1 or GPT-5.4 nano better for coding?
They score almost the same on coding (44.0 vs 43.6); test both on your own repository before choosing.
How many benchmarks do ERNIE 5.1 and GPT-5.4 nano share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-5.4 nano has 40.