Model comparison
Llama 3-8B vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 25.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
NVIDIASummary
- They share 17 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Nemotron 4 340b Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 4 340b Instruct leads 31.4 to 7.8.
Side by side
| Llama 3-8B | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 25.3 | 35.3 |
| Released | 2024-04-18 | 2024-06-14 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 34 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Llama 3-8B: 30.5 (#285), Nemotron 4 340b Instruct: 34.6 (#223)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1152 | 1209 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Nemotron 4 340b Instruct leads
Llama 3-8B: 13.8 (#321), Nemotron 4 340b Instruct: 22.4 (#180)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1202 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Nemotron 4 340b Instruct leads
Llama 3-8B: 8.3 (#317), Nemotron 4 340b Instruct: 31.7 (#193)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1151 | 1216 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Nemotron 4 340b Instruct leads
Llama 3-8B: 7.8 (#303), Nemotron 4 340b Instruct: 31.4 (#212)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1113 | 1171 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Nemotron 4 340b Instruct leads
Llama 3-8B: 31.0 (#256), Nemotron 4 340b Instruct: 38.0 (#228)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1098 | 1206 |
| LMArena Chinese | 1076 | 1214 |
| LMArena French | 1158 | 1196 |
| LMArena German | 1104 | 1192 |
| LMArena Japanese | 967 | 1128 |
| LMArena Korean | 1003 | 1148 |
| LMArena Russian | 1109 | 1219 |
| LMArena Spanish | 1172 | 1195 |
Instruction Following Nemotron 4 340b Instruct leads
Llama 3-8B: 58.7 (#255), Nemotron 4 340b Instruct: 63.3 (#227)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1127 | 1203 |
Long Context Nemotron 4 340b Instruct leads
Llama 3-8B: 34.2 (#246), Nemotron 4 340b Instruct: 37.1 (#216)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1128 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
Llama 3-8B: 37.7 (#251), Nemotron 4 340b Instruct: 42.9 (#229)
| Benchmark | Llama 3-8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1166 | 1225 |
| LMArena Creative Writing | 1150 | 1203 |
| LMArena Multi-Turn | 1152 | 1214 |
Frequently asked questions
Is Llama 3-8B better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 25.3 on the Noometry Index.
Is Llama 3-8B or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 34.6 versus 30.5 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Nemotron 4 340b Instruct share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Nemotron 4 340b Instruct has 17.