Model comparison
Amazon Nova Lite vs Gemma 2B
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Amazon Nova Lite scores higher in 6 categories and Gemma 2B in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Lite leads 42.1 to 24.0.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Gemma 2B | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 31.9 | 29.6 |
| Released | 2024-12-03 | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Lite leads
Amazon Nova Lite: 32.5 (#270), Gemma 2B: 29.4 (#305)
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Coding | 1239 | 1010 |
| LiveBench Coding | 27.5% | — |
| ALE-Bench | 236.25 | — |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning Too close to call
Amazon Nova Lite: 19.3 (#260), Gemma 2B: 18.8 (#275)
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 989 |
| LiveBench Reasoning | 36.7% | — |
| LiveBench Data Analysis | 37.2% | — |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 94.2 |
| HellaSwag | — | 71.4% |
| LiveBench | 36.4% | — |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math Gemma 2B leads
Amazon Nova Lite: 27.8 (#247), Gemma 2B: 30.0 (#239)
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Math | 1227 | 1009 |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Amazon Nova Lite: 26.3 (#259), Gemma 2B: —
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| MMLU | 77% | 42.3% |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| LMArena Expert | 1201 | — |
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| TriviaQA | — | 53.2% |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), Gemma 2B: —
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Amazon Nova Lite leads
Amazon Nova Lite: 38.0 (#232), Gemma 2B: 23.0 (#294)
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1208 | 958 |
| LMArena Chinese | 1225 | 986 |
| LMArena Russian | 1216 | 937 |
| LMArena French | 1237 | — |
| LMArena German | 1229 | — |
| LMArena Japanese | 1153 | — |
| LMArena Korean | 1153 | — |
| LMArena Spanish | 1226 | — |
Instruction Following Amazon Nova Lite leads
Amazon Nova Lite: 59.3 (#255), Gemma 2B: 48.5 (#302)
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1205 | 970 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#217), Gemma 2B: 29.9 (#291)
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1234 | 981 |
Writing & Preference Amazon Nova Lite leads
Amazon Nova Lite: 42.1 (#237), Gemma 2B: 24.0 (#308)
| Benchmark | Amazon Nova Lite | Gemma 2B |
|---|---|---|
| LMArena Text | 1229 | 1002 |
| LMArena Creative Writing | 1197 | 987 |
| LMArena Multi-Turn | 1199 | 945 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Gemma 2B?
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.6 on the Noometry Index.
Is Amazon Nova Lite or Gemma 2B better for coding?
Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 29.4 in the Noometry coding category.
How many benchmarks do Amazon Nova Lite and Gemma 2B share?
12 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Gemma 2B has 23.