Model comparison
Nemotron 4 340b Instruct vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 35.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. Nemotron 4 340b Instruct scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 42.7.
Side by side
| Nemotron 4 340b Instruct | Step 3 | |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 35.9 | 40.5 |
| Released | 2024-06-14 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Nemotron 4 340b Instruct: 35.2 (#228), Step 3: 40.1 (#147)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Coding | 1209 | 1367 |
Reasoning Step 3 leads
Nemotron 4 340b Instruct: 23.4 (#178), Step 3: 28.4 (#105)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1202 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Nemotron 4 340b Instruct: 34.3 (#195), Step 3: 37.6 (#148)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Math | 1216 | 1366 |
Knowledge Step 3 leads
Nemotron 4 340b Instruct: 32.0 (#216), Step 3: 36.8 (#164)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Expert | 1171 | 1333 |
Multimodal Not comparable
Nemotron 4 340b Instruct: —, Step 3: 35.5 (#86)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Nemotron 4 340b Instruct: 37.9 (#233), Step 3: 46.3 (#159)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | 1206 | 1327 |
| LMArena Chinese | 1214 | 1397 |
| LMArena German | 1192 | 1371 |
| LMArena Korean | 1148 | 1269 |
| LMArena Russian | 1219 | 1331 |
| LMArena Spanish | 1195 | 1371 |
| LMArena French | 1197 | — |
| LMArena Japanese | 1128 | — |
Instruction Following Step 3 leads
Nemotron 4 340b Instruct: 63.1 (#232), Step 3: 70.4 (#164)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1203 | 1332 |
Long Context Step 3 leads
Nemotron 4 340b Instruct: 37.1 (#221), Step 3: 40.3 (#157)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | 1225 | 1326 |
Writing & Preference Step 3 leads
Nemotron 4 340b Instruct: 42.7 (#233), Step 3: 54.3 (#151)
| Benchmark | Nemotron 4 340b Instruct | Step 3 |
|---|---|---|
| LMArena Text | 1225 | 1350 |
| LMArena Creative Writing | 1203 | 1321 |
| LMArena Multi-Turn | 1214 | 1341 |
Frequently asked questions
Is Nemotron 4 340b Instruct better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 35.9 on the Noometry Index.
Is Nemotron 4 340b Instruct or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 35.2 in the Noometry coding category.
How many benchmarks do Nemotron 4 340b Instruct and Step 3 share?
15 benchmarks have published results for both models. Nemotron 4 340b Instruct has 17 scored results on Noometry and Step 3 has 17.