Model comparison
DeepSeek-V3.1-Terminus vs Nemotron 3 Ultra
DeepSeek-V3.1-Terminus and Nemotron 3 Ultra score almost the same on the Noometry Index (43.1 vs 42.5), 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-V3.1-Terminus scores higher in 2 categories and Nemotron 3 Ultra in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 61.0.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 90.1% for Nemotron 3 Ultra.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1-Terminus | Nemotron 3 Ultra | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 43.1 | 42.5 |
| Released | 2025-09-22 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 147K | 128K |
| Input $ / M tokens | $0.27 | $0.50 |
| Output $ / M tokens | $1 | $2.20 |
| Results tracked | 16 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 40.6% | 40.3% |
| LMArena Coding | 1426 | 1468 |
| FrontierCode | — | 13.6% |
| WeirdML | — | 43.5% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 1.7% | 3.1% |
| LMArena Hard Prompts | 1426 | 1452 |
| DTBench | 81.3% | 90.1% |
| LMCA | 28.6% | 36.9% |
| Kagi LLM Benchmark | 57.4% | — |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| Epoch Capabilities Index | — | 146.17 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1402 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |
Multilingual Nemotron 3 Ultra leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1407 | 1427 |
| LMArena Russian | 1436 | 1417 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Spanish | — | 1454 |
Instruction Following Too close to call
DeepSeek-V3.1-Terminus: 74.0 (#106), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1404 | 1418 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.4 (#97), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1421 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | DeepSeek-V3.1-Terminus | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1419 | 1445 |
| LMArena Creative Writing | 1403 | 1398 |
| LMArena Multi-Turn | 1411 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Nemotron 3 Ultra?
DeepSeek-V3.1-Terminus and Nemotron 3 Ultra score almost the same on the Noometry Index (43.1 vs 42.5), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1-Terminus or Nemotron 3 Ultra?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is DeepSeek-V3.1-Terminus or Nemotron 3 Ultra better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Nemotron 3 Ultra share?
14 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Nemotron 3 Ultra has 30.