Model comparison
Nova 2 Lite vs Qwen2.5 72B Instruct
Nova 2 Lite is the stronger model overall, scoring 39.7 to 31.9 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 Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova 2 Lite leads 37.5 to 19.3.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Nova 2 Lite accepts more context: 1M tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Nova 2 Lite | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 39.7 | 31.9 |
| Released | 2025-12-01 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 64K | 8K |
| Input $ / M tokens | $0.30 | $1.40 |
| Output $ / M tokens | $2.50 | $5.60 |
| Results tracked | 19 | 43 |
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), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1385 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Nova 2 Lite leads
Nova 2 Lite: 24.1 (#121), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Nova 2 Lite leads
Nova 2 Lite: 27.5 (#118), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Nova 2 Lite leads
Nova 2 Lite: 37.5 (#156), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1359 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Nova 2 Lite leads
Nova 2 Lite: 43.0 (#94), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1358 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Nova 2 Lite leads
Nova 2 Lite: 47.1 (#153), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1337 | 1252 |
| LMArena Chinese | 1364 | 1272 |
| LMArena French | 1381 | 1280 |
| LMArena German | 1343 | 1234 |
| LMArena Japanese | 1271 | 1180 |
| LMArena Korean | 1284 | 1188 |
| LMArena Russian | 1343 | 1264 |
| LMArena Spanish | 1373 | 1256 |
Instruction Following Nova 2 Lite leads
Nova 2 Lite: 70.5 (#161), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1335 | 1254 |
| IFEval | — | 80.6% |
Long Context Nova 2 Lite leads
Nova 2 Lite: 40.6 (#150), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1335 | 1282 |
Writing & Preference Nova 2 Lite leads
Nova 2 Lite: 53.9 (#154), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Nova 2 Lite | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1362 | 1269 |
| LMArena Creative Writing | 1291 | 1221 |
| LMArena Multi-Turn | 1338 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Nova 2 Lite better than Qwen2.5 72B Instruct?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 31.9 on the Noometry Index.
Which is cheaper, Nova 2 Lite or Qwen2.5 72B Instruct?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Nova 2 Lite or Qwen2.5 72B Instruct better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 131K.
How many benchmarks do Nova 2 Lite and Qwen2.5 72B Instruct share?
17 benchmarks have published results for both models. Nova 2 Lite has 19 scored results on Noometry and Qwen2.5 72B Instruct has 43.