Model comparison
Llama 3.1-405B vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 30.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
Meta
NVIDIASummary
- They share 16 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Nemotron 3 Super in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Super leads 37.6 to 17.3.
- The biggest single-benchmark swing is WeirdML: 21.4% for Llama 3.1-405B and 38% for Nemotron 3 Super.
Side by side
| Llama 3.1-405B | Nemotron 3 Super | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.4 | 39.6 |
| Released | 2024-07-23 | 2026-03-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.45 |
| Results tracked | 42 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Llama 3.1-405B: 32.7 (#257), Nemotron 3 Super: 38.9 (#153)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| WeirdML | 21.4% | 38% |
| LMArena Coding | 1291 | 1403 |
| SciCode | — | 36% |
| ALE-Bench | — | 213.9 |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 20.9 (#131), Nemotron 3 Super: —
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Nemotron 3 Super leads
Llama 3.1-405B: 16.4 (#293), Nemotron 3 Super: 17.9 (#274)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1270 | 1386 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.76 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Nemotron 3 Super leads
Llama 3.1-405B: 17.3 (#283), Nemotron 3 Super: 37.6 (#95)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1281 | 1381 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Nemotron 3 Super leads
Llama 3.1-405B: 30.4 (#221), Nemotron 3 Super: 38.2 (#136)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1243 | 1397 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Nemotron 3 Super leads
Llama 3.1-405B: 40.9 (#209), Nemotron 3 Super: 48.6 (#139)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1248 | 1356 |
| LMArena Chinese | 1242 | 1430 |
| LMArena French | 1278 | 1404 |
| LMArena German | 1252 | 1341 |
| LMArena Russian | 1265 | 1336 |
| LMArena Spanish | 1259 | 1417 |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
Instruction Following Nemotron 3 Super leads
Llama 3.1-405B: 66.1 (#209), Nemotron 3 Super: 71.4 (#149)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1259 | 1347 |
| IFEval | 81.1% | — |
Long Context Nemotron 3 Super leads
Llama 3.1-405B: 38.4 (#192), Nemotron 3 Super: 41.5 (#134)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1266 | 1362 |
Writing & Preference Nemotron 3 Super leads
Llama 3.1-405B: 39.1 (#246), Nemotron 3 Super: 56.1 (#135)
| Benchmark | Llama 3.1-405B | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1284 | 1378 |
| LMArena Creative Writing | 1262 | 1317 |
| LMArena Multi-Turn | 1297 | 1369 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 30.4 on the Noometry Index.
Is Llama 3.1-405B or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 32.7 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Nemotron 3 Super share?
16 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Nemotron 3 Super has 21.