Model comparison
Llama 3-70B vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 28.8 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
NVIDIASummary
- They share 20 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and Nemotron 3 Ultra in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Llama 3-70B and 86.7% for Nemotron 3 Ultra.
Side by side
| Llama 3-70B | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 28.8 | 42.5 |
| Released | 2024-04-18 | 2026-06-04 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 31 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Llama 3-70B: 35.8 (#218), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1206 | 1468 |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Nemotron 3 Ultra leads
Llama 3-70B: 21.1 (#139), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| Cybench | 5% | — |
Reasoning Nemotron 3 Ultra leads
Llama 3-70B: 18.0 (#288), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1452 |
| DTBench | 54.2% | 90.1% |
| Epoch Capabilities Index | 122.93 | 146.17 |
| Kagi LLM Benchmark | 35.1% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| LMCA | — | 36.9% |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Nemotron 3 Ultra leads
Llama 3-70B: 12.8 (#305), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 86.7% |
| LMArena Math | 1218 | 1457 |
| ProofBench | — | 2% |
| MATH Level 5 | 22.6% | — |
Knowledge Nemotron 3 Ultra leads
Llama 3-70B: 20.8 (#277), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 40.6% | 85.4% |
| LMArena Expert | 1149 | 1472 |
| MMLU | 79.3% | — |
Multilingual Nemotron 3 Ultra leads
Llama 3-70B: 33.6 (#251), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1142 | 1427 |
| LMArena Chinese | 1114 | 1497 |
| LMArena French | 1232 | 1472 |
| LMArena German | 1169 | 1471 |
| LMArena Korean | 1017 | 1386 |
| LMArena Russian | 1159 | 1417 |
| LMArena Spanish | 1241 | 1454 |
| LMArena Japanese | 1017 | — |
Instruction Following Nemotron 3 Ultra leads
Llama 3-70B: 62.5 (#238), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1194 | 1418 |
Long Context Nemotron 3 Ultra leads
Llama 3-70B: 35.6 (#240), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1174 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Llama 3-70B: 42.8 (#231), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Llama 3-70B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1221 | 1445 |
| LMArena Creative Writing | 1210 | 1398 |
| LMArena Multi-Turn | 1223 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is Llama 3-70B better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 28.8 on the Noometry Index.
Is Llama 3-70B or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Nemotron 3 Ultra share?
20 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Nemotron 3 Ultra has 30.