Model comparison
Llama 3.2 90B vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.0 to 27.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in math, where Nova 2 Lite leads 34.8 to 10.4.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | Nova 2 Lite | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 27.1 | 39.0 |
| Released | 2024-09-24 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 9 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Nova 2 Lite: 40.1 (#131)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| LMArena Coding | — | 1386 |
Agentic & Tool Use Llama 3.2 90B leads
Llama 3.2 90B: 29.7 (#73), Nova 2 Lite: 23.9 (#114)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
| BALROG | 27.3% | — |
Reasoning Nova 2 Lite leads
Llama 3.2 90B: 20.9 (#207), Nova 2 Lite: 26.4 (#120)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1364 |
| Epoch Capabilities Index | 125.5 | — |
Math Nova 2 Lite leads
Llama 3.2 90B: 10.4 (#302), Nova 2 Lite: 34.8 (#154)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1359 |
| MATH Level 5 | 39.4% | — |
Knowledge Nova 2 Lite leads
Llama 3.2 90B: 21.7 (#269), Nova 2 Lite: 42.5 (#88)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| GPQA Diamond | 41% | — |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1360 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 24.9 (#119), Nova 2 Lite: —
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Nova 2 Lite: 47.3 (#148)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | — | 1337 |
| LMArena Chinese | — | 1364 |
| LMArena French | — | 1381 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1273 |
| LMArena Korean | — | 1284 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1372 |
Instruction Following Not comparable
Llama 3.2 90B: —, Nova 2 Lite: 70.7 (#156)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | — | 1335 |
Long Context Not comparable
Llama 3.2 90B: —, Nova 2 Lite: 40.6 (#145)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | — | 1335 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Nova 2 Lite: 54.1 (#150)
| Benchmark | Llama 3.2 90B | Nova 2 Lite |
|---|---|---|
| LMArena Text | — | 1362 |
| LMArena Creative Writing | — | 1291 |
| LMArena Multi-Turn | — | 1338 |
Frequently asked questions
Is Llama 3.2 90B better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.0 to 27.1 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Nova 2 Lite share?
0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Nova 2 Lite has 19.