Model comparison
DeepSeek-V2.5 (Sep 2024) vs Llama 3.1 Nemotron 70b Instruct
DeepSeek-V2.5 (Sep 2024) and Llama 3.1 Nemotron 70b Instruct score almost the same on the Noometry Index (37.6 vs 37.6), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 14 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Llama 3.1 Nemotron 70b Instruct in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Llama 3.1 Nemotron 70b Instruct leads 35.9 to 31.7.
- The biggest single-benchmark swing is BigCodeBench Instruct: 48.6% for DeepSeek-V2.5 (Sep 2024) and 38.7% for Llama 3.1 Nemotron 70b Instruct.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 37.6 | 37.6 |
| Released | 2024-09-06 | 2024-12-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1 Nemotron 70b Instruct leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Llama 3.1 Nemotron 70b Instruct: 35.9 (#216)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.6% | 38.7% |
| LMArena Coding | 1309 | 1272 |
| BigCodeBench Complete | 53.2% | 48.2% |
| Aider Polyglot | 17.8% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Too close to call
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Llama 3.1 Nemotron 70b Instruct: 25.0 (#152)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1266 |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Llama 3.1 Nemotron 70b Instruct: 35.5 (#182)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Math | 1288 | 1271 |
Knowledge Too close to call
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Llama 3.1 Nemotron 70b Instruct: 34.1 (#199)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Expert | 1266 | 1242 |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Llama 3.1 Nemotron 70b Instruct: 40.5 (#217)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Non-English | 1273 | 1245 |
| LMArena Chinese | 1318 | 1263 |
| LMArena Russian | 1289 | 1227 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Llama 3.1 Nemotron 70b Instruct: 65.9 (#213)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Instruction Following | 1280 | 1252 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Llama 3.1 Nemotron 70b Instruct: 37.6 (#215)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Longer Query | 1301 | 1238 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Llama 3.1 Nemotron 70b Instruct: 48.4 (#203)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Text | 1294 | 1283 |
| LMArena Creative Writing | 1285 | 1269 |
| LMArena Multi-Turn | 1297 | 1275 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Llama 3.1 Nemotron 70b Instruct?
DeepSeek-V2.5 (Sep 2024) and Llama 3.1 Nemotron 70b Instruct score almost the same on the Noometry Index (37.6 vs 37.6), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or Llama 3.1 Nemotron 70b Instruct better for coding?
Llama 3.1 Nemotron 70b Instruct scores higher on coding benchmarks: 35.9 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Llama 3.1 Nemotron 70b Instruct share?
14 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Llama 3.1 Nemotron 70b Instruct has 14.