Model comparison
DeepSeek-V3.1 vs Nemotron 4 340b Instruct
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 35.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Nemotron 4 340b Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 42.9.
Side by side
| DeepSeek-V3.1 | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 42.2 | 35.3 |
| Released | 2025-08-21 | 2024-06-14 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 39.8 (#140), Nemotron 4 340b Instruct: 34.6 (#223)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1417 | 1209 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), Nemotron 4 340b Instruct: 22.4 (#180)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1202 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.1 (#125), Nemotron 4 340b Instruct: 31.7 (#193)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1420 | 1216 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.0 (#86), Nemotron 4 340b Instruct: 31.4 (#212)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1403 | 1171 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.8 (#100), Nemotron 4 340b Instruct: 38.0 (#228)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1400 | 1206 |
| LMArena Chinese | 1470 | 1214 |
| LMArena French | 1447 | 1196 |
| LMArena German | 1412 | 1192 |
| LMArena Japanese | 1374 | 1128 |
| LMArena Korean | 1337 | 1148 |
| LMArena Russian | 1405 | 1219 |
| LMArena Spanish | 1429 | 1195 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 74.1 (#105), Nemotron 4 340b Instruct: 63.3 (#227)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1400 | 1203 |
Long Context Too close to call
DeepSeek-V3.1: 36.3 (#227), Nemotron 4 340b Instruct: 37.1 (#216)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1422 | 1225 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.5 (#93), Nemotron 4 340b Instruct: 42.9 (#229)
| Benchmark | DeepSeek-V3.1 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1420 | 1225 |
| LMArena Creative Writing | 1401 | 1203 |
| LMArena Multi-Turn | 1408 | 1214 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Nemotron 4 340b Instruct?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 35.3 on the Noometry Index.
Is DeepSeek-V3.1 or Nemotron 4 340b Instruct better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 34.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Nemotron 4 340b Instruct share?
17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Nemotron 4 340b Instruct has 17.