Model comparison
Llama 3.1-405B vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.7 to 30.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Nova 2 Lite in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova 2 Lite leads 37.5 to 18.4.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Nova 2 Lite | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 30.7 | 39.7 |
| Released | 2024-07-23 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 42 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Llama 3.1-405B: 33.1 (#262), Nova 2 Lite: 40.7 (#134)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1291 | 1385 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Nova 2 Lite leads
Llama 3.1-405B: 21.0 (#140), Nova 2 Lite: 24.1 (#121)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Nova 2 Lite leads
Llama 3.1-405B: 16.8 (#300), Nova 2 Lite: 27.5 (#118)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1364 |
| 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 Nova 2 Lite leads
Llama 3.1-405B: 18.4 (#290), Nova 2 Lite: 37.5 (#156)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1281 | 1359 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Nova 2 Lite leads
Llama 3.1-405B: 30.4 (#227), Nova 2 Lite: 43.0 (#94)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1243 | 1358 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| Vectara Hallucination Rate | — | 5.1% |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Nova 2 Lite leads
Llama 3.1-405B: 40.7 (#214), Nova 2 Lite: 47.1 (#153)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1248 | 1337 |
| LMArena Chinese | 1242 | 1364 |
| LMArena French | 1279 | 1381 |
| LMArena German | 1252 | 1343 |
| LMArena Japanese | 1208 | 1271 |
| LMArena Korean | 1184 | 1284 |
| LMArena Russian | 1265 | 1343 |
| LMArena Spanish | 1260 | 1373 |
Instruction Following Nova 2 Lite leads
Llama 3.1-405B: 65.9 (#214), Nova 2 Lite: 70.5 (#161)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1259 | 1335 |
| IFEval | 81.1% | — |
Long Context Nova 2 Lite leads
Llama 3.1-405B: 38.4 (#197), Nova 2 Lite: 40.6 (#150)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1266 | 1335 |
Writing & Preference Nova 2 Lite leads
Llama 3.1-405B: 38.9 (#251), Nova 2 Lite: 53.9 (#154)
| Benchmark | Llama 3.1-405B | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1284 | 1362 |
| LMArena Creative Writing | 1262 | 1291 |
| LMArena Multi-Turn | 1297 | 1338 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Nova 2 Lite share?
17 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Nova 2 Lite has 19.