Model comparison
Llama 3.1-405B vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 30.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
NVIDIASummary
- They share 17 benchmarks with published results for both. Llama 3.1-405B scores higher in 3 categories and Nemotron 4 340b Instruct in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 4 340b Instruct leads 34.3 to 18.4.
Side by side
| Llama 3.1-405B | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.7 | 35.9 |
| Released | 2024-07-23 | 2024-06-14 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Llama 3.1-405B: 33.1 (#262), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1291 | 1209 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Nemotron 4 340b Instruct: —
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Nemotron 4 340b Instruct leads
Llama 3.1-405B: 16.8 (#300), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1202 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Nemotron 4 340b Instruct leads
Llama 3.1-405B: 18.4 (#290), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1281 | 1216 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Nemotron 4 340b Instruct leads
Llama 3.1-405B: 30.4 (#227), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1243 | 1171 |
| 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 Llama 3.1-405B leads
Llama 3.1-405B: 40.7 (#214), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1248 | 1206 |
| LMArena Chinese | 1242 | 1214 |
| LMArena French | 1279 | 1197 |
| LMArena German | 1252 | 1192 |
| LMArena Japanese | 1208 | 1128 |
| LMArena Korean | 1184 | 1148 |
| LMArena Russian | 1265 | 1219 |
| LMArena Spanish | 1260 | 1195 |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 65.9 (#214), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1259 | 1203 |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1266 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
Llama 3.1-405B: 38.9 (#251), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Llama 3.1-405B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1284 | 1225 |
| LMArena Creative Writing | 1262 | 1203 |
| LMArena Multi-Turn | 1297 | 1214 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Nemotron 4 340b Instruct share?
17 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Nemotron 4 340b Instruct has 17.