Model comparison
DeepSeek-V3.1 vs Nemotron 3 Super
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 40.1 on the Noometry Index. Nemotron 3 Super costs 2.5× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 16 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 6 categories and Nemotron 3 Super in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 18.7.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- Nemotron 3 Super accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1 | Nemotron 3 Super | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 42.8 | 40.1 |
| Released | 2025-08-21 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $0.08 |
| Output $ / M tokens | $0.95 | $0.45 |
| Results tracked | 27 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.1: 40.3 (#144), Nemotron 3 Super: 39.4 (#158)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| WeirdML | 38.4% | 38% |
| LMArena Coding | 1417 | 1403 |
| SciCode | — | 36% |
| ALE-Bench | — | 213.9 |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Nemotron 3 Super: 18.7 (#276)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1386 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Too close to call
DeepSeek-V3.1: 38.9 (#122), Nemotron 3 Super: 39.6 (#101)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1420 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Nemotron 3 Super: 38.9 (#139)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1405 | 1398 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Nemotron 3 Super: 48.4 (#144)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1400 | 1355 |
| LMArena Chinese | 1469 | 1432 |
| LMArena French | 1447 | 1405 |
| LMArena German | 1411 | 1341 |
| LMArena Russian | 1405 | 1336 |
| LMArena Spanish | 1431 | 1417 |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Nemotron 3 Super: 71.2 (#154)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1400 | 1347 |
Long Context Nemotron 3 Super leads
DeepSeek-V3.1: 36.3 (#232), Nemotron 3 Super: 41.5 (#139)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1422 | 1362 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Nemotron 3 Super: 55.9 (#140)
| Benchmark | DeepSeek-V3.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1420 | 1378 |
| LMArena Creative Writing | 1401 | 1317 |
| LMArena Multi-Turn | 1408 | 1369 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Nemotron 3 Super?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 40.1 on the Noometry Index. Nemotron 3 Super costs 2.5× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1 or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.
Is DeepSeek-V3.1 or Nemotron 3 Super better for coding?
They score almost the same on coding (40.3 vs 39.4); test both on your own repository before choosing.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Nemotron 3 Super share?
16 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Nemotron 3 Super has 21.