Model comparison
Amazon Nova Micro vs Qwen2-72B
Amazon Nova Micro and Qwen2-72B score almost the same on the Noometry Index (30.4 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 5 categories and Qwen2-72B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Amazon Nova Micro leads 29.6 to 21.2.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Qwen2-72B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 30.4 | 30.0 |
| Released | 2024-12-03 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Micro leads
Amazon Nova Micro: 30.5 (#295), Qwen2-72B: 29.1 (#310)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1218 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LiveBench Coding | 20.2% | — |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Amazon Nova Micro leads
Amazon Nova Micro: 22.1 (#132), Qwen2-72B: 17.0 (#146)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Amazon Nova Micro: 17.4 (#294), Qwen2-72B: 23.2 (#181)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1191 |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| Epoch Capabilities Index | — | 125.28 |
| LiveBench | 29.6% | — |
Math Qwen2-72B leads
Amazon Nova Micro: 26.9 (#254), Qwen2-72B: 30.2 (#236)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Math | 1206 | 1235 |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Amazon Nova Micro leads
Amazon Nova Micro: 29.6 (#237), Qwen2-72B: 21.2 (#275)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1184 | 1171 |
| MMLU | 70.8% | 82.4% |
| GPQA Diamond | — | 40.8% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual Too close to call
Amazon Nova Micro: 36.5 (#239), Qwen2-72B: 35.9 (#244)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1186 | 1176 |
| LMArena Chinese | 1209 | 1240 |
| LMArena French | 1238 | 1170 |
| LMArena German | 1192 | 1151 |
| LMArena Japanese | 1154 | 1111 |
| LMArena Korean | 1150 | 1083 |
| LMArena Russian | 1185 | 1169 |
| LMArena Spanish | 1225 | 1169 |
Instruction Following Qwen2-72B leads
Amazon Nova Micro: 56.3 (#272), Qwen2-72B: 61.7 (#241)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1181 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Too close to call
Amazon Nova Micro: 36.5 (#229), Qwen2-72B: 36.1 (#235)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1205 | 1192 |
Writing & Preference Qwen2-72B leads
Amazon Nova Micro: 39.5 (#247), Qwen2-72B: 40.8 (#241)
| Benchmark | Amazon Nova Micro | Qwen2-72B |
|---|---|---|
| LMArena Text | 1208 | 1203 |
| LMArena Creative Writing | 1172 | 1181 |
| LMArena Multi-Turn | 1178 | 1196 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Qwen2-72B?
Amazon Nova Micro and Qwen2-72B score almost the same on the Noometry Index (30.4 vs 30.0), so choose on price, context window or the category you care about most.
Is Amazon Nova Micro or Qwen2-72B better for coding?
Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 29.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Micro and Qwen2-72B share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Qwen2-72B has 26.