Model comparison
Nemotron 3 Ultra vs o3-mini
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 36.7 on the Noometry Index.
Last verified . 26 shared benchmarks.
NVIDIASummary
- They share 26 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 6 categories and o3-mini in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 50.3.
- The biggest single-benchmark swing is DTBench: 90.1% for Nemotron 3 Ultra and 68.8% for o3-mini.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- 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 | o3-mini | |
|---|---|---|
| Provider | NVIDIA | OpenAI |
| Noometry Index | 42.5 | 36.7 |
| Released | 2026-06-04 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.50 | $1.10 |
| Output $ / M tokens | $2.20 | $4.40 |
| Results tracked | 30 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Nemotron 3 Ultra: 38.1 (#182), o3-mini: 40.8 (#132)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| SciCode | 40.3% | 39.8% |
| WeirdML | 43.5% | 43.7% |
| LMArena Coding | 1468 | 1378 |
| FrontierCode | 13.6% | — |
| Aider Polyglot | — | 60.4% |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use o3-mini leads
Nemotron 3 Ultra: 23.4 (#126), o3-mini: 29.6 (#84)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| APEX-Agents | 22.7% | — |
| Cybench | — | 22.5% |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 31.0 (#82), o3-mini: 16.3 (#305)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| CritPt | 3.1% | 0.3% |
| Chess Puzzles | 12% | 17% |
| LMArena Hard Prompts | 1452 | 1366 |
| Mystery Game Puzzles | 20% | 7% |
| DTBench | 90.1% | 68.8% |
| LMCA | 36.9% | 19% |
| Epoch Capabilities Index | 146.17 | 140.34 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Nemotron 3 Ultra leads
Nemotron 3 Ultra: 35.3 (#187), o3-mini: 28.1 (#244)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 76.9% |
| LMArena Math | 1457 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| ProofBench | 2% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#61), o3-mini: 38.3 (#146)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| GPQA Diamond | 85.4% | 77% |
| LMArena Expert | 1472 | 1364 |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.5 (#64), o3-mini: 45.7 (#164)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| LMArena Non-English | 1427 | 1319 |
| LMArena Chinese | 1497 | 1379 |
| LMArena French | 1472 | 1334 |
| LMArena German | 1471 | 1303 |
| LMArena Korean | 1386 | 1314 |
| LMArena Russian | 1417 | 1304 |
| LMArena Spanish | 1454 | 1321 |
| LMArena Japanese | — | 1286 |
Instruction Following Too close to call
Nemotron 3 Ultra: 74.7 (#88), o3-mini: 75.1 (#72)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1418 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Nemotron 3 Ultra leads
Nemotron 3 Ultra: 43.9 (#81), o3-mini: 33.8 (#256)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| LMArena Longer Query | 1437 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#36), o3-mini: 50.3 (#182)
| Benchmark | Nemotron 3 Ultra | o3-mini |
|---|---|---|
| LMArena Text | 1445 | 1337 |
| LMArena Creative Writing | 1398 | 1286 |
| LMArena Multi-Turn | 1411 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1692 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Nemotron 3 Ultra better than o3-mini?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 36.7 on the Noometry Index.
Which is cheaper, Nemotron 3 Ultra or o3-mini?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Nemotron 3 Ultra or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 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 o3-mini share?
26 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and o3-mini has 51.