Model comparison
ERNIE 5.1 vs Nemotron 3.5 Lightning
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 40.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
NVIDIASummary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Nemotron 3.5 Lightning in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 48.5.
- Nemotron 3.5 Lightning has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Nemotron 3.5 Lightning | |
|---|---|---|
| Provider | Baidu | NVIDIA |
| Noometry Index | 43.8 | 40.0 |
| Released | — | 2026-08-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 19 | 18 |
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), Nemotron 3.5 Lightning: 40.4 (#141)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Coding | 1488 | 1375 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Nemotron 3.5 Lightning: —
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Nemotron 3.5 Lightning leads
ERNIE 5.1: 21.9 (#211), Nemotron 3.5 Lightning: 26.8 (#127)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1337 |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Nemotron 3.5 Lightning: 37.5 (#155)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | 1481 | 1359 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Nemotron 3.5 Lightning: 37.5 (#154)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | 1492 | 1356 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Nemotron 3.5 Lightning: 44.0 (#180)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | 1454 | 1295 |
| LMArena Chinese | 1508 | 1359 |
| LMArena French | 1488 | 1366 |
| LMArena German | 1470 | 1282 |
| LMArena Japanese | 1422 | 1206 |
| LMArena Korean | 1427 | 1238 |
| LMArena Russian | 1459 | 1253 |
| LMArena Spanish | 1473 | 1345 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Nemotron 3.5 Lightning: 69.6 (#170)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | 1460 | 1318 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Nemotron 3.5 Lightning: 39.9 (#165)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | 1462 | 1314 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Nemotron 3.5 Lightning: 48.5 (#201)
| Benchmark | ERNIE 5.1 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | 1468 | 1327 |
| LMArena Creative Writing | 1441 | 1254 |
| LMArena Multi-Turn | 1471 | 1328 |
| EQ-Bench Creative Writing | — | 1280 |
Frequently asked questions
Is ERNIE 5.1 better than Nemotron 3.5 Lightning?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 40.0 on the Noometry Index.
Is ERNIE 5.1 or Nemotron 3.5 Lightning better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 40.4 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Nemotron 3.5 Lightning share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Nemotron 3.5 Lightning has 18.