Model comparison
Nova 2 Lite vs Qwen2-72B
Nova 2 Lite is the stronger model overall, scoring 39.7 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Nova 2 Lite scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nova 2 Lite leads 43.0 to 21.2.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Nova 2 Lite | Qwen2-72B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 39.7 | 30.0 |
| Released | 2025-12-01 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 19 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Nova 2 Lite: 40.7 (#134), Qwen2-72B: 29.1 (#310)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1385 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Nova 2 Lite leads
Nova 2 Lite: 24.1 (#121), Qwen2-72B: 17.0 (#146)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Nova 2 Lite leads
Nova 2 Lite: 27.5 (#118), Qwen2-72B: 23.2 (#181)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Nova 2 Lite leads
Nova 2 Lite: 37.5 (#156), Qwen2-72B: 30.2 (#236)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Math | 1359 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Nova 2 Lite leads
Nova 2 Lite: 43.0 (#94), Qwen2-72B: 21.2 (#275)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1358 | 1171 |
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | — | 82.4% |
Multilingual Nova 2 Lite leads
Nova 2 Lite: 47.1 (#153), Qwen2-72B: 35.9 (#244)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1337 | 1176 |
| LMArena Chinese | 1364 | 1240 |
| LMArena French | 1381 | 1170 |
| LMArena German | 1343 | 1151 |
| LMArena Japanese | 1271 | 1111 |
| LMArena Korean | 1284 | 1083 |
| LMArena Russian | 1343 | 1169 |
| LMArena Spanish | 1373 | 1169 |
Instruction Following Nova 2 Lite leads
Nova 2 Lite: 70.5 (#161), Qwen2-72B: 61.7 (#241)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1335 | 1181 |
Long Context Nova 2 Lite leads
Nova 2 Lite: 40.6 (#150), Qwen2-72B: 36.1 (#235)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1335 | 1192 |
Writing & Preference Nova 2 Lite leads
Nova 2 Lite: 53.9 (#154), Qwen2-72B: 40.8 (#241)
| Benchmark | Nova 2 Lite | Qwen2-72B |
|---|---|---|
| LMArena Text | 1362 | 1203 |
| LMArena Creative Writing | 1291 | 1181 |
| LMArena Multi-Turn | 1338 | 1196 |
Frequently asked questions
Is Nova 2 Lite better than Qwen2-72B?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 30.0 on the Noometry Index.
Is Nova 2 Lite or Qwen2-72B better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 29.1 in the Noometry coding category.
How many benchmarks do Nova 2 Lite and Qwen2-72B share?
17 benchmarks have published results for both models. Nova 2 Lite has 19 scored results on Noometry and Qwen2-72B has 26.