Model comparison
Nemotron 3 Ultra vs o1
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 40.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
NVIDIASummary
- They share 23 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 4 categories and o1 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 41.5.
- The biggest single-benchmark swing is DTBench: 90.1% for Nemotron 3 Ultra and 74.7% for o1.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $15 / $60 for o1.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 200K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Nemotron 3 Ultra | o1 | |
|---|---|---|
| Provider | NVIDIA | OpenAI |
| Noometry Index | 42.5 | 40.9 |
| Released | 2026-06-04 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.50 | $15 |
| Output $ / M tokens | $2.20 | $60 |
| Results tracked | 30 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Nemotron 3 Ultra: 38.1 (#182), o1: 46.1 (#70)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| WeirdML | 43.5% | 47.6% |
| LMArena Coding | 1468 | 1367 |
| FrontierCode | 13.6% | — |
| Aider Polyglot | — | 61.7% |
| SciCode | 40.3% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use o1 leads
Nemotron 3 Ultra: 23.4 (#126), o1: 24.6 (#117)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| APEX-Agents | 22.7% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 31.0 (#82), o1: 27.9 (#111)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| Chess Puzzles | 12% | 15% |
| LMArena Hard Prompts | 1452 | 1371 |
| DTBench | 90.1% | 74.7% |
| LMCA | 36.9% | 22.3% |
| Epoch Capabilities Index | 146.17 | 141.91 |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| CritPt | 3.1% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 20% | — |
| LiveBench Data Analysis | — | 65.5% |
| LiveBench | — | 75.7% |
Math Too close to call
Nemotron 3 Ultra: 35.3 (#187), o1: 36.1 (#175)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 73.3% |
| LMArena Math | 1457 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| ProofBench | 2% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#61), o1: 41.5 (#110)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| GPQA Diamond | 85.4% | 76.8% |
| LMArena Expert | 1472 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
Multimodal Not comparable
Nemotron 3 Ultra: —, o1: 34.2 (#93)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.5 (#64), o1: 48.6 (#142)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| LMArena Non-English | 1427 | 1358 |
| LMArena Chinese | 1497 | 1394 |
| LMArena French | 1472 | 1344 |
| LMArena German | 1471 | 1337 |
| LMArena Korean | 1386 | 1396 |
| LMArena Russian | 1417 | 1356 |
| LMArena Spanish | 1454 | 1345 |
| LMArena Japanese | — | 1346 |
Instruction Following Too close to call
Nemotron 3 Ultra: 74.7 (#88), o1: 74.8 (#86)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| LMArena Instruction Following | 1418 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Nemotron 3 Ultra: 43.9 (#81), o1: 50.3 (#9)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| LMArena Longer Query | 1437 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#36), o1: 55.6 (#144)
| Benchmark | Nemotron 3 Ultra | o1 |
|---|---|---|
| LMArena Text | 1445 | 1366 |
| LMArena Creative Writing | 1398 | 1348 |
| LMArena Multi-Turn | 1411 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1692 | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Nemotron 3 Ultra better than o1?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 40.9 on the Noometry Index.
Which is cheaper, Nemotron 3 Ultra or o1?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; o1 lists at $15 and $60.
Is Nemotron 3 Ultra or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 200K.
How many benchmarks do Nemotron 3 Ultra and o1 share?
23 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and o1 has 52.