Model comparison
Llama 3.2 90B vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 27.5 on the Noometry Index.
Last verified . 3 shared benchmarks.
Meta
NVIDIASummary
- They share 3 benchmarks with published results for both. Llama 3.2 90B scores higher in 1 category and Nemotron 3 Ultra in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 21.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 86.7% for Nemotron 3 Ultra.
Side by side
| Llama 3.2 90B | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 27.5 | 42.5 |
| Released | 2024-09-24 | 2026-06-04 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 9 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| LMArena Coding | — | 1468 |
Agentic & Tool Use Llama 3.2 90B leads
Llama 3.2 90B: 30.0 (#80), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| BALROG | 27.3% | — |
Reasoning Nemotron 3 Ultra leads
Llama 3.2 90B: 21.7 (#217), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 146.17 |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1452 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
Math Nemotron 3 Ultra leads
Llama 3.2 90B: 11.1 (#308), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 86.7% |
| ProofBench | — | 2% |
| LMArena Math | — | 1457 |
| MATH Level 5 | 39.4% | — |
Knowledge Nemotron 3 Ultra leads
Llama 3.2 90B: 21.7 (#274), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 41% | 85.4% |
| LMArena Expert | — | 1472 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), Nemotron 3 Ultra: —
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |
Instruction Following Not comparable
Llama 3.2 90B: —, Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | — | 1418 |
Long Context Not comparable
Llama 3.2 90B: —, Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Llama 3.2 90B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | — | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |
Frequently asked questions
Is Llama 3.2 90B better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Nemotron 3 Ultra share?
3 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Nemotron 3 Ultra has 30.