Model comparison
Llama 3-70B vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.7 to 28.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 3-70B 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 12.8.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | Nova 2 Lite | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 28.8 | 39.7 |
| Released | 2024-04-18 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 31 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Llama 3-70B: 35.8 (#218), Nova 2 Lite: 40.7 (#134)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1206 | 1385 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Nova 2 Lite leads
Llama 3-70B: 21.1 (#139), Nova 2 Lite: 24.1 (#121)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
| Cybench | 5% | — |
Reasoning Nova 2 Lite leads
Llama 3-70B: 18.0 (#288), Nova 2 Lite: 27.5 (#118)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1364 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Nova 2 Lite leads
Llama 3-70B: 12.8 (#305), Nova 2 Lite: 37.5 (#156)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1218 | 1359 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge Nova 2 Lite leads
Llama 3-70B: 20.8 (#277), Nova 2 Lite: 43.0 (#94)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1149 | 1358 |
| GPQA Diamond | 40.6% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | 79.3% | — |
Multilingual Nova 2 Lite leads
Llama 3-70B: 33.6 (#251), Nova 2 Lite: 47.1 (#153)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1142 | 1337 |
| LMArena Chinese | 1114 | 1364 |
| LMArena French | 1232 | 1381 |
| LMArena German | 1169 | 1343 |
| LMArena Japanese | 1017 | 1271 |
| LMArena Korean | 1017 | 1284 |
| LMArena Russian | 1159 | 1343 |
| LMArena Spanish | 1241 | 1373 |
Instruction Following Nova 2 Lite leads
Llama 3-70B: 62.5 (#238), Nova 2 Lite: 70.5 (#161)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1194 | 1335 |
Long Context Nova 2 Lite leads
Llama 3-70B: 35.6 (#240), Nova 2 Lite: 40.6 (#150)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1174 | 1335 |
Writing & Preference Nova 2 Lite leads
Llama 3-70B: 42.8 (#231), Nova 2 Lite: 53.9 (#154)
| Benchmark | Llama 3-70B | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1221 | 1362 |
| LMArena Creative Writing | 1210 | 1291 |
| LMArena Multi-Turn | 1223 | 1338 |
Frequently asked questions
Is Llama 3-70B better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 28.8 on the Noometry Index.
Is Llama 3-70B or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Nova 2 Lite share?
17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Nova 2 Lite has 19.