Model comparison
DeepSeek LLM 67B vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 24.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Nemotron 4 340b Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 4 340b Instruct leads 31.4 to 7.1.
Side by side
| DeepSeek LLM 67B | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 24.8 | 35.3 |
| Released | 2023-11-29 | 2024-06-14 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 31.3 (#273), Nemotron 4 340b Instruct: 34.6 (#223)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1096 | 1209 |
Reasoning Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 15.9 (#300), Nemotron 4 340b Instruct: 22.4 (#180)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1202 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 8.1 (#318), Nemotron 4 340b Instruct: 31.7 (#193)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1108 | 1216 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 7.1 (#308), Nemotron 4 340b Instruct: 31.4 (#212)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1171 |
Multilingual Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 29.5 (#262), Nemotron 4 340b Instruct: 38.0 (#228)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1073 | 1206 |
| LMArena Chinese | 1132 | 1214 |
| LMArena French | — | 1196 |
| LMArena German | — | 1192 |
| LMArena Japanese | — | 1128 |
| LMArena Korean | — | 1148 |
| LMArena Russian | — | 1219 |
| LMArena Spanish | — | 1195 |
Instruction Following Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 55.7 (#272), Nemotron 4 340b Instruct: 63.3 (#227)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1079 | 1203 |
Long Context Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 33.1 (#260), Nemotron 4 340b Instruct: 37.1 (#216)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1092 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
DeepSeek LLM 67B: 31.8 (#277), Nemotron 4 340b Instruct: 42.9 (#229)
| Benchmark | DeepSeek LLM 67B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1105 | 1225 |
| LMArena Creative Writing | 1067 | 1203 |
| LMArena Multi-Turn | 1082 | 1214 |
Frequently asked questions
Is DeepSeek LLM 67B better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 34.6 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Nemotron 4 340b Instruct share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Nemotron 4 340b Instruct has 17.