Model comparison
Llama 3.1-405B vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 30.7 on the Noometry Index.
Last verified . 6 shared benchmarks.
MetaSummary
- They share 6 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Nova Premier 1.0 in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova Premier 1.0 leads 33.8 to 18.4.
- The biggest single-benchmark swing is Omni-MATH: 24.9% for Llama 3.1-405B and 35% for Nova Premier 1.0.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Nova Premier 1.0 | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 30.7 | 38.3 |
| Released | 2024-07-23 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 10K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $12.50 |
| Results tracked | 42 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1-405B: 33.1 (#262), Nova Premier 1.0: —
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| WeirdML | 21.4% | — |
| LMArena Coding | 1291 | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Nova Premier 1.0: —
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Nova Premier 1.0 leads
Llama 3.1-405B: 16.8 (#300), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 45% | 44.8% |
| SimpleBench | 23% | — |
| LMArena Hard Prompts | 1269 | — |
| 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 Nova Premier 1.0 leads
Llama 3.1-405B: 18.4 (#290), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | 24.9% | 35% |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| LMArena Math | 1281 | — |
| MATH Level 5 | 49.8% | — |
Knowledge Nova Premier 1.0 leads
Llama 3.1-405B: 30.4 (#227), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | 72.3% | 72.6% |
| GPQA (HELM) | 52.2% | 51.8% |
| GPQA Diamond | 50.9% | — |
| Confabulations | 17.6% | — |
| LMArena Expert | 1243 | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Not comparable
Llama 3.1-405B: 40.7 (#214), Nova Premier 1.0: —
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1248 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1279 | — |
| LMArena German | 1252 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1265 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Too close to call
Llama 3.1-405B: 65.9 (#214), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| IFEval | 81.1% | 80.3% |
| LMArena Instruction Following | 1259 | — |
Long Context Not comparable
Llama 3.1-405B: 38.4 (#197), Nova Premier 1.0: —
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1266 | — |
Writing & Preference Nova Premier 1.0 leads
Llama 3.1-405B: 38.9 (#251), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Llama 3.1-405B | Nova Premier 1.0 |
|---|---|---|
| WildBench | 78.3% | 78.8% |
| LMArena Text | 1284 | — |
| LMArena Creative Writing | 1262 | — |
| EQ-Bench Creative Writing | 870 | — |
| LMArena Multi-Turn | 1297 | — |
Frequently asked questions
Is Llama 3.1-405B better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 30.7 on the Noometry Index.
How many benchmarks do Llama 3.1-405B and Nova Premier 1.0 share?
6 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Nova Premier 1.0 has 6.