Model comparison
Deepseek Coder v2 vs Llama 3.1 Nemotron 70b Instruct
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 35.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 14 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Llama 3.1 Nemotron 70b Instruct in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3.1 Nemotron 70b Instruct leads 48.4 to 38.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.7% for Deepseek Coder v2 and 48.2% for Llama 3.1 Nemotron 70b Instruct.
Side by side
| Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 35.9 | 37.6 |
| Released | 2024-06-17 | 2024-12-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 14 |
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), Llama 3.1 Nemotron 70b Instruct: 35.9 (#216)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 38.7% |
| LMArena Coding | 1251 | 1272 |
| BigCodeBench Complete | 59.7% | 48.2% |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Llama 3.1 Nemotron 70b Instruct leads
Deepseek Coder v2: 23.6 (#176), Llama 3.1 Nemotron 70b Instruct: 25.0 (#152)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1266 |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 34.9 (#190), Llama 3.1 Nemotron 70b Instruct: 35.5 (#182)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Math | 1241 | 1271 |
| GSM8K | 94.5% | — |
Knowledge Llama 3.1 Nemotron 70b Instruct leads
Deepseek Coder v2: 32.3 (#212), Llama 3.1 Nemotron 70b Instruct: 34.1 (#199)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Expert | 1181 | 1242 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Llama 3.1 Nemotron 70b Instruct leads
Deepseek Coder v2: 36.3 (#240), Llama 3.1 Nemotron 70b Instruct: 40.5 (#217)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Non-English | 1182 | 1245 |
| LMArena Chinese | 1201 | 1263 |
| LMArena Russian | 1188 | 1227 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Llama 3.1 Nemotron 70b Instruct leads
Deepseek Coder v2: 61.7 (#242), Llama 3.1 Nemotron 70b Instruct: 65.9 (#213)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Instruction Following | 1180 | 1252 |
Long Context Too close to call
Deepseek Coder v2: 37.0 (#224), Llama 3.1 Nemotron 70b Instruct: 37.6 (#215)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Longer Query | 1219 | 1238 |
Writing & Preference Llama 3.1 Nemotron 70b Instruct leads
Deepseek Coder v2: 38.2 (#253), Llama 3.1 Nemotron 70b Instruct: 48.4 (#203)
| Benchmark | Deepseek Coder v2 | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Text | 1191 | 1283 |
| LMArena Creative Writing | 1120 | 1269 |
| LMArena Multi-Turn | 1177 | 1275 |
Frequently asked questions
Is Deepseek Coder v2 better than Llama 3.1 Nemotron 70b Instruct?
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Llama 3.1 Nemotron 70b Instruct better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 35.9 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Llama 3.1 Nemotron 70b Instruct share?
14 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Llama 3.1 Nemotron 70b Instruct has 14.