Model comparison
DeepSeek-R1-Distill-Qwen-32B vs Llama 3.1 Nemotron 70b Instruct
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 35.5 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 2 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-32B scores higher in 3 categories and Llama 3.1 Nemotron 70b Instruct in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Llama 3.1 Nemotron 70b Instruct leads 25.0 to 18.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 54.9% for DeepSeek-R1-Distill-Qwen-32B and 48.2% for Llama 3.1 Nemotron 70b Instruct.
Side by side
| DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 35.5 | 37.6 |
| Released | 2025-01-20 | 2024-12-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212), Llama 3.1 Nemotron 70b Instruct: 35.9 (#216)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| BigCodeBench Instruct | 43.9% | 38.7% |
| BigCodeBench Complete | 54.9% | 48.2% |
| LiveBench Coding | 33.7% | — |
| LMArena Coding | — | 1272 |
Agentic & Tool Use Not comparable
DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94), Llama 3.1 Nemotron 70b Instruct: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| BALROG | 19.5% | — |
Reasoning Llama 3.1 Nemotron 70b Instruct leads
DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284), Llama 3.1 Nemotron 70b Instruct: 25.0 (#152)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 52.3% | — |
| LMArena Hard Prompts | — | 1266 |
| LiveBench Data Analysis | 45.4% | — |
| Epoch Capabilities Index | 137.44 | — |
| LiveBench | 45.5% | — |
Math Llama 3.1 Nemotron 70b Instruct leads
DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194), Llama 3.1 Nemotron 70b Instruct: 35.5 (#182)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| LiveBench Math | 59.4% | — |
| LMArena Math | — | 1271 |
Knowledge DeepSeek-R1-Distill-Qwen-32B leads
DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182), Llama 3.1 Nemotron 70b Instruct: 34.1 (#199)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| GPQA Diamond | 64.1% | — |
| LMArena Expert | — | 1242 |
Multilingual Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Llama 3.1 Nemotron 70b Instruct: 40.5 (#217)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Non-English | — | 1245 |
| LMArena Chinese | — | 1263 |
| LMArena Russian | — | 1227 |
Instruction Following Llama 3.1 Nemotron 70b Instruct leads
DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243), Llama 3.1 Nemotron 70b Instruct: 65.9 (#213)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LiveBench Instruction Following | 55.7% | — |
| LMArena Instruction Following | — | 1252 |
Long Context Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Llama 3.1 Nemotron 70b Instruct: 37.6 (#215)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1238 |
Writing & Preference DeepSeek-R1-Distill-Qwen-32B leads
DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188), Llama 3.1 Nemotron 70b Instruct: 48.4 (#203)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Text | — | 1283 |
| LMArena Creative Writing | — | 1269 |
| LMArena Multi-Turn | — | 1275 |
| LiveBench Language | 26.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-32B better than Llama 3.1 Nemotron 70b Instruct?
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 35.5 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-32B or Llama 3.1 Nemotron 70b Instruct better for coding?
They score almost the same on coding (36.1 vs 35.9); test both on your own repository before choosing.
How many benchmarks do DeepSeek-R1-Distill-Qwen-32B and Llama 3.1 Nemotron 70b Instruct share?
2 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-32B has 14 scored results on Noometry and Llama 3.1 Nemotron 70b Instruct has 14.