Model comparison
Amazon Nova Lite vs Qwen-14B
Amazon Nova Lite and Qwen-14B score almost the same on the Noometry Index (31.9 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Amazon Nova Lite scores higher in 5 categories and Qwen-14B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Lite leads 42.1 to 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Qwen-14B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 31.9 | 31.4 |
| Released | 2024-12-03 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 18 |
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), Qwen-14B: 31.2 (#288)
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Coding | 1239 | 1071 |
| LiveBench Coding | 27.5% | — |
| ALE-Bench | 236.25 | — |
Reasoning Too close to call
Amazon Nova Lite: 19.3 (#260), Qwen-14B: 19.6 (#257)
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1027 |
| LiveBench Reasoning | 36.7% | — |
| LiveBench Data Analysis | 37.2% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| LiveBench | 36.4% | — |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Amazon Nova Lite: 27.8 (#247), Qwen-14B: 31.2 (#227)
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Math | 1227 | 1068 |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Amazon Nova Lite: 26.3 (#259), Qwen-14B: —
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| MMLU | 77% | 66.3% |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| LMArena Expert | 1201 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), Qwen-14B: —
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Amazon Nova Lite leads
Amazon Nova Lite: 38.0 (#232), Qwen-14B: 27.5 (#275)
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1208 | 1041 |
| LMArena Chinese | 1225 | 1077 |
| LMArena French | 1237 | — |
| LMArena German | 1229 | — |
| LMArena Japanese | 1153 | — |
| LMArena Korean | 1153 | — |
| LMArena Russian | 1216 | — |
| LMArena Spanish | 1226 | — |
Instruction Following Amazon Nova Lite leads
Amazon Nova Lite: 59.3 (#255), Qwen-14B: 52.4 (#289)
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1205 | 1031 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#217), Qwen-14B: 31.3 (#280)
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1234 | 1028 |
Writing & Preference Amazon Nova Lite leads
Amazon Nova Lite: 42.1 (#237), Qwen-14B: 27.6 (#299)
| Benchmark | Amazon Nova Lite | Qwen-14B |
|---|---|---|
| LMArena Text | 1229 | 1051 |
| LMArena Creative Writing | 1197 | 1028 |
| LMArena Multi-Turn | 1199 | 1022 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Qwen-14B?
Amazon Nova Lite and Qwen-14B score almost the same on the Noometry Index (31.9 vs 31.4), so choose on price, context window or the category you care about most.
Is Amazon Nova Lite or Qwen-14B better for coding?
Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 31.2 in the Noometry coding category.
How many benchmarks do Amazon Nova Lite and Qwen-14B share?
11 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Qwen-14B has 18.