Model comparison
Nemotron 3.5 Lightning vs Step 3
Nemotron 3.5 Lightning and Step 3 score almost the same on the Noometry Index (40.0 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
NVIDIA
StepFunSummary
- They share 15 benchmarks with published results for both. Nemotron 3.5 Lightning scores higher in 2 categories and Step 3 in 6 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 48.5.
Side by side
| Nemotron 3.5 Lightning | Step 3 | |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 40.0 | 40.5 |
| Released | 2026-08-11 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.20 | — |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Nemotron 3.5 Lightning: 40.4 (#141), Step 3: 40.1 (#147)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Coding | 1375 | 1367 |
Reasoning Step 3 leads
Nemotron 3.5 Lightning: 26.8 (#127), Step 3: 28.4 (#105)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1337 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Too close to call
Nemotron 3.5 Lightning: 37.5 (#155), Step 3: 37.6 (#148)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Math | 1359 | 1366 |
Knowledge Too close to call
Nemotron 3.5 Lightning: 37.5 (#154), Step 3: 36.8 (#164)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Expert | 1356 | 1333 |
Multimodal Not comparable
Nemotron 3.5 Lightning: —, Step 3: 35.5 (#86)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Nemotron 3.5 Lightning: 44.0 (#180), Step 3: 46.3 (#159)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Non-English | 1295 | 1327 |
| LMArena Chinese | 1359 | 1397 |
| LMArena German | 1282 | 1371 |
| LMArena Korean | 1238 | 1269 |
| LMArena Russian | 1253 | 1331 |
| LMArena Spanish | 1345 | 1371 |
| LMArena French | 1366 | — |
| LMArena Japanese | 1206 | — |
Instruction Following Too close to call
Nemotron 3.5 Lightning: 69.6 (#170), Step 3: 70.4 (#164)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1332 |
Long Context Too close to call
Nemotron 3.5 Lightning: 39.9 (#165), Step 3: 40.3 (#157)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Longer Query | 1314 | 1326 |
Writing & Preference Step 3 leads
Nemotron 3.5 Lightning: 48.5 (#201), Step 3: 54.3 (#151)
| Benchmark | Nemotron 3.5 Lightning | Step 3 |
|---|---|---|
| LMArena Text | 1327 | 1350 |
| LMArena Creative Writing | 1254 | 1321 |
| LMArena Multi-Turn | 1328 | 1341 |
| EQ-Bench Creative Writing | 1280 | — |
Frequently asked questions
Is Nemotron 3.5 Lightning better than Step 3?
Nemotron 3.5 Lightning and Step 3 score almost the same on the Noometry Index (40.0 vs 40.5), so choose on price, context window or the category you care about most.
Is Nemotron 3.5 Lightning or Step 3 better for coding?
They score almost the same on coding (40.4 vs 40.1); test both on your own repository before choosing.
How many benchmarks do Nemotron 3.5 Lightning and Step 3 share?
15 benchmarks have published results for both models. Nemotron 3.5 Lightning has 18 scored results on Noometry and Step 3 has 17.