Model comparison
Deepseek Coder v2 vs Nemotron 4 340b Instruct
Deepseek Coder v2 and Nemotron 4 340b Instruct score almost the same on the Noometry Index (35.9 vs 35.9), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 4 categories and Nemotron 4 340b Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 4 340b Instruct leads 42.7 to 38.2.
Side by side
| Deepseek Coder v2 | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 35.9 | 35.9 |
| Released | 2024-06-17 | 2024-06-14 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1251 | 1209 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Too close to call
Deepseek Coder v2: 23.6 (#176), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1202 |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 34.9 (#190), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1241 | 1216 |
| GSM8K | 94.5% | — |
Knowledge Too close to call
Deepseek Coder v2: 32.3 (#212), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1181 | 1171 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Nemotron 4 340b Instruct leads
Deepseek Coder v2: 36.3 (#240), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1182 | 1206 |
| LMArena Chinese | 1201 | 1214 |
| LMArena French | 1185 | 1197 |
| LMArena German | 1164 | 1192 |
| LMArena Japanese | 1126 | 1128 |
| LMArena Korean | 1104 | 1148 |
| LMArena Russian | 1188 | 1219 |
| LMArena Spanish | 1153 | 1195 |
Instruction Following Nemotron 4 340b Instruct leads
Deepseek Coder v2: 61.7 (#242), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1180 | 1203 |
Long Context Too close to call
Deepseek Coder v2: 37.0 (#224), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1219 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
Deepseek Coder v2: 38.2 (#253), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Deepseek Coder v2 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1191 | 1225 |
| LMArena Creative Writing | 1120 | 1203 |
| LMArena Multi-Turn | 1177 | 1214 |
Frequently asked questions
Is Deepseek Coder v2 better than Nemotron 4 340b Instruct?
Deepseek Coder v2 and Nemotron 4 340b Instruct score almost the same on the Noometry Index (35.9 vs 35.9), so choose on price, context window or the category you care about most.
Is Deepseek Coder v2 or Nemotron 4 340b Instruct better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 35.2 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Nemotron 4 340b Instruct share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Nemotron 4 340b Instruct has 17.