Model comparison
DeepSeek LLM 67B vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 24.9 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 3 Super in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Super leads 38.9 to 7.0.
Side by side
| DeepSeek LLM 67B | Nemotron 3 Super | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 24.9 | 40.1 |
| Released | 2023-11-29 | 2026-03-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.45 |
| Results tracked | 15 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
DeepSeek LLM 67B: 31.9 (#278), Nemotron 3 Super: 39.4 (#158)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| LMArena Coding | 1096 | 1403 |
| SciCode | — | 36% |
| WeirdML | — | 38% |
| ALE-Bench | — | 213.9 |
Reasoning Nemotron 3 Super leads
DeepSeek LLM 67B: 16.5 (#304), Nemotron 3 Super: 18.7 (#276)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1386 |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Nemotron 3 Super leads
DeepSeek LLM 67B: 8.7 (#324), Nemotron 3 Super: 39.6 (#101)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1108 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Nemotron 3 Super leads
DeepSeek LLM 67B: 7.0 (#313), Nemotron 3 Super: 38.9 (#139)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1398 |
Multilingual Nemotron 3 Super leads
DeepSeek LLM 67B: 29.4 (#267), Nemotron 3 Super: 48.4 (#144)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1073 | 1355 |
| LMArena Chinese | 1132 | 1432 |
| LMArena French | — | 1405 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1336 |
| LMArena Spanish | — | 1417 |
Instruction Following Nemotron 3 Super leads
DeepSeek LLM 67B: 55.4 (#277), Nemotron 3 Super: 71.2 (#154)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1079 | 1347 |
Long Context Nemotron 3 Super leads
DeepSeek LLM 67B: 33.1 (#265), Nemotron 3 Super: 41.5 (#139)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1092 | 1362 |
Writing & Preference Nemotron 3 Super leads
DeepSeek LLM 67B: 31.6 (#282), Nemotron 3 Super: 55.9 (#140)
| Benchmark | DeepSeek LLM 67B | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1105 | 1378 |
| LMArena Creative Writing | 1067 | 1317 |
| LMArena Multi-Turn | 1082 | 1369 |
Frequently asked questions
Is DeepSeek LLM 67B better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Nemotron 3 Super share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Nemotron 3 Super has 21.