Model comparison
Nova 2.0 Pro Preview vs Qwen2.5 72B Instruct
Nova 2.0 Pro Preview is the stronger model overall, scoring 33.4 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in coding, where Nova 2.0 Pro Preview leads 40.8 to 33.2.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Nova 2.0 Pro Preview | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 33.4 | 31.9 |
| Released | 2025-12-02 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 3 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2.0 Pro Preview leads
Nova 2.0 Pro Preview: 40.8 (#133), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| SciCode | 42.7% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1292 |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Too close to call
Nova 2.0 Pro Preview: 21.9 (#136), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| GDP.pdf | 2% | — |
| METR Time Horizons | — | 35.8% |
Reasoning Too close to call
Nova 2.0 Pro Preview: 22.4 (#194), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 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 Not comparable
Nova 2.0 Pro Preview: —, Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge Not comparable
Nova 2.0 Pro Preview: —, Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Not comparable
Nova 2.0 Pro Preview: —, Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |
Instruction Following Not comparable
Nova 2.0 Pro Preview: —, Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
Nova 2.0 Pro Preview: —, Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Not comparable
Nova 2.0 Pro Preview: —, Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Nova 2.0 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |
Frequently asked questions
Is Nova 2.0 Pro Preview better than Qwen2.5 72B Instruct?
Nova 2.0 Pro Preview is the stronger model overall, scoring 33.4 to 31.9 on the Noometry Index.
Is Nova 2.0 Pro Preview or Qwen2.5 72B Instruct better for coding?
Nova 2.0 Pro Preview scores higher on coding benchmarks: 40.8 versus 33.2 in the Noometry coding category.
How many benchmarks do Nova 2.0 Pro Preview and Qwen2.5 72B Instruct share?
0 benchmarks have published results for both models. Nova 2.0 Pro Preview has 3 scored results on Noometry and Qwen2.5 72B Instruct has 43.