Model comparison
Amazon Nova Lite vs Qwen2.5 72B Instruct
Amazon Nova Lite and Qwen2.5 72B Instruct score almost the same on the Noometry Index (31.9 vs 31.9), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Amazon Nova Lite scores higher in 1 category and Qwen2.5 72B Instruct in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Lite leads 27.8 to 19.3.
- The biggest single-benchmark swing is Omni-MATH: 23.3% for Amazon Nova Lite and 33% for Qwen2.5 72B Instruct.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Amazon Nova Lite accepts more context: 300K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 31.9 | 31.9 |
| Released | 2024-12-03 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 300K | 131K |
| Max output | 10K | 8K |
| Input $ / M tokens | $0.06 | $1.40 |
| Output $ / M tokens | $0.24 | $5.60 |
| Results tracked | 34 | 43 |
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), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1239 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LiveBench Coding | 27.5% | — |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 236.25 | — |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Amazon Nova Lite: 19.3 (#260), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1271 |
| LiveBench Reasoning | 36.7% | — |
| DTBench | — | 62.9% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| LiveBench | 36.4% | — |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Amazon Nova Lite leads
Amazon Nova Lite: 27.8 (#247), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| Omni-MATH | 23.3% | 33% |
| LMArena Math | 1227 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 63.2% |
Knowledge Too close to call
Amazon Nova Lite: 26.3 (#259), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| MMLU-Pro | 60% | 63.1% |
| GPQA (HELM) | 39.7% | 42.6% |
| LMArena Expert | 1201 | 1245 |
| MMLU | 77% | 85.3% |
| GPQA Diamond | — | 49.1% |
| Humanity's Last Exam | 3.6% | — |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 6.1% | — |
| ARC (AI2) Challenge | — | 94.5% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), Qwen2.5 72B Instruct: —
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Qwen2.5 72B Instruct leads
Amazon Nova Lite: 38.0 (#232), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1208 | 1252 |
| LMArena Chinese | 1225 | 1272 |
| LMArena French | 1237 | 1280 |
| LMArena German | 1229 | 1234 |
| LMArena Japanese | 1153 | 1180 |
| LMArena Korean | 1153 | 1188 |
| LMArena Russian | 1216 | 1264 |
| LMArena Spanish | 1226 | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Amazon Nova Lite: 59.3 (#255), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 77.6% | 80.6% |
| LMArena Instruction Following | 1205 | 1254 |
| LiveBench Instruction Following | 54.1% | — |
Long Context Qwen2.5 72B Instruct leads
Amazon Nova Lite: 37.4 (#217), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1234 | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Amazon Nova Lite: 42.1 (#237), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Amazon Nova Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1229 | 1269 |
| LMArena Creative Writing | 1197 | 1221 |
| WildBench | 75% | 80.2% |
| LMArena Multi-Turn | 1199 | 1272 |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Qwen2.5 72B Instruct?
Amazon Nova Lite and Qwen2.5 72B Instruct score almost the same on the Noometry Index (31.9 vs 31.9), so choose on price, context window or the category you care about most.
Which is cheaper, Amazon Nova Lite or Qwen2.5 72B Instruct?
Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Amazon Nova Lite or Qwen2.5 72B Instruct better for coding?
They score almost the same on coding (32.5 vs 33.2); test both on your own repository before choosing.
Which has the bigger context window?
Amazon Nova Lite does, with 300K tokens against 131K.
How many benchmarks do Amazon Nova Lite and Qwen2.5 72B Instruct share?
23 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Qwen2.5 72B Instruct has 43.