Model comparison
Nova 2.0 Pro Preview vs Qwen3-1.7B
Nova 2.0 Pro Preview is the stronger model overall, scoring 33.4 to 26.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Nova 2.0 Pro Preview leads 22.4 to 19.2.
- Qwen3-1.7B has downloadable open weights; the other is API-only.
Side by side
| Nova 2.0 Pro Preview | Qwen3-1.7B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 33.4 | 26.6 |
| Released | 2025-12-02 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 3 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nova 2.0 Pro Preview: 40.8 (#133), Qwen3-1.7B: —
| Benchmark | Nova 2.0 Pro Preview | Qwen3-1.7B |
|---|---|---|
| SciCode | 42.7% | — |
Agentic & Tool Use Qwen3-1.7B leads
Nova 2.0 Pro Preview: 21.9 (#136), Qwen3-1.7B: 24.7 (#115)
| Benchmark | Nova 2.0 Pro Preview | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |
| GDP.pdf | 2% | — |
Reasoning Nova 2.0 Pro Preview leads
Nova 2.0 Pro Preview: 22.4 (#194), Qwen3-1.7B: 19.2 (#267)
| Benchmark | Nova 2.0 Pro Preview | Qwen3-1.7B |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
Math Not comparable
Nova 2.0 Pro Preview: —, Qwen3-1.7B: 16.3 (#294)
| Benchmark | Nova 2.0 Pro Preview | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
Knowledge Not comparable
Nova 2.0 Pro Preview: —, Qwen3-1.7B: 19.6 (#278)
| Benchmark | Nova 2.0 Pro Preview | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
Frequently asked questions
Is Nova 2.0 Pro Preview better than Qwen3-1.7B?
Nova 2.0 Pro Preview is the stronger model overall, scoring 33.4 to 26.6 on the Noometry Index.
How many benchmarks do Nova 2.0 Pro Preview and Qwen3-1.7B share?
0 benchmarks have published results for both models. Nova 2.0 Pro Preview has 3 scored results on Noometry and Qwen3-1.7B has 4.