Model comparison
Llama 3-8B vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 25.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
NVIDIASummary
- They share 15 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Nemotron 3 Super in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Super leads 38.2 to 7.8.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
- Nemotron 3 Super accepts more context: 262K tokens versus 8K.
Side by side
| Llama 3-8B | Nemotron 3 Super | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 25.3 | 39.6 |
| Released | 2024-04-18 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.14 | $0.08 |
| Output $ / M tokens | $0.14 | $0.45 |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Llama 3-8B: 30.5 (#285), Nemotron 3 Super: 38.9 (#153)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Coding | 1152 | 1403 |
| SciCode | — | 36% |
| WeirdML | — | 38% |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| ALE-Bench | — | 213.9 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Nemotron 3 Super leads
Llama 3-8B: 13.8 (#321), Nemotron 3 Super: 17.9 (#274)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1386 |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Nemotron 3 Super leads
Llama 3-8B: 8.3 (#317), Nemotron 3 Super: 37.6 (#95)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1151 | 1381 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Nemotron 3 Super leads
Llama 3-8B: 7.8 (#303), Nemotron 3 Super: 38.2 (#136)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1113 | 1397 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Nemotron 3 Super leads
Llama 3-8B: 31.0 (#256), Nemotron 3 Super: 48.6 (#139)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1098 | 1356 |
| LMArena Chinese | 1076 | 1430 |
| LMArena French | 1158 | 1404 |
| LMArena German | 1104 | 1341 |
| LMArena Russian | 1109 | 1336 |
| LMArena Spanish | 1172 | 1417 |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
Instruction Following Nemotron 3 Super leads
Llama 3-8B: 58.7 (#255), Nemotron 3 Super: 71.4 (#149)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1127 | 1347 |
Long Context Nemotron 3 Super leads
Llama 3-8B: 34.2 (#246), Nemotron 3 Super: 41.5 (#134)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1128 | 1362 |
Writing & Preference Nemotron 3 Super leads
Llama 3-8B: 37.7 (#251), Nemotron 3 Super: 56.1 (#135)
| Benchmark | Llama 3-8B | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1166 | 1378 |
| LMArena Creative Writing | 1150 | 1317 |
| LMArena Multi-Turn | 1152 | 1369 |
Frequently asked questions
Is Llama 3-8B better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 25.3 on the Noometry Index.
Which is cheaper, Llama 3-8B or Nemotron 3 Super?
Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is Llama 3-8B or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 8K.
How many benchmarks do Llama 3-8B and Nemotron 3 Super share?
15 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Nemotron 3 Super has 21.