Model comparison
Amazon Nova Lite vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Amazon Nova Lite scores higher in 3 categories and Qwen1.5-110B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-110B leads 33.7 to 27.8.
- Qwen1.5-110B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Qwen1.5-110B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 31.9 | 34.2 |
| Released | 2024-12-03 | 2024-04-25 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Lite: 32.5 (#270), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1239 | 1184 |
| BigCodeBench Instruct | — | 35% |
| LiveBench Coding | 27.5% | — |
| BigCodeBench Complete | — | 44.4% |
| ALE-Bench | 236.25 | — |
Reasoning Qwen1.5-110B leads
Amazon Nova Lite: 19.3 (#260), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1168 |
| LiveBench Reasoning | 36.7% | — |
| LiveBench Data Analysis | 37.2% | — |
| ForecastBench | — | 57.7 |
| LiveBench | 36.4% | — |
Math Qwen1.5-110B leads
Amazon Nova Lite: 27.8 (#247), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1227 | 1185 |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
Knowledge Qwen1.5-110B leads
Amazon Nova Lite: 26.3 (#259), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1201 | 1144 |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), Qwen1.5-110B: —
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Amazon Nova Lite leads
Amazon Nova Lite: 38.0 (#232), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1208 | 1142 |
| LMArena Chinese | 1225 | 1206 |
| LMArena French | 1237 | 1151 |
| LMArena German | 1229 | 1123 |
| LMArena Japanese | 1153 | 1074 |
| LMArena Korean | 1153 | 1044 |
| LMArena Russian | 1216 | 1118 |
| LMArena Spanish | 1226 | 1142 |
Instruction Following Too close to call
Amazon Nova Lite: 59.3 (#255), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1205 | 1158 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#217), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1234 | 1157 |
Writing & Preference Amazon Nova Lite leads
Amazon Nova Lite: 42.1 (#237), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Amazon Nova Lite | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1229 | 1175 |
| LMArena Creative Writing | 1197 | 1148 |
| LMArena Multi-Turn | 1199 | 1160 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.9 on the Noometry Index.
Is Amazon Nova Lite or Qwen1.5-110B better for coding?
They score almost the same on coding (32.5 vs 33.0); test both on your own repository before choosing.
How many benchmarks do Amazon Nova Lite and Qwen1.5-110B share?
17 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Qwen1.5-110B has 20.