Model comparison
Nova Premier 1.0 vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 38.8 to 37.7 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Nova Premier 1.0 scores higher in 1 category and Qwen3 32B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 37.9 to 31.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 44.8% for Nova Premier 1.0 and 54.9% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 131K.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| Nova Premier 1.0 | Qwen3 32B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 37.7 | 38.8 |
| Released | 2025-04-30 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 10K | 16K |
| Input $ / M tokens | $2.50 | $0.70 |
| Output $ / M tokens | $12.50 | $2.80 |
| Results tracked | 6 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nova Premier 1.0: —, Qwen3 32B: 37.3 (#184)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| LMArena Coding | — | 1358 |
Agentic & Tool Use Not comparable
Nova Premier 1.0: —, Qwen3 32B: 32.3 (#58)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Nova Premier 1.0 leads
Nova Premier 1.0: 22.3 (#182), Qwen3 32B: 19.6 (#233)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 44.8% | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | — | 1335 |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Nova Premier 1.0: 31.5 (#194), Qwen3 32B: 37.9 (#89)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| Omni-MATH | 35% | — |
| LMArena Math | — | 1399 |
Knowledge Qwen3 32B leads
Nova Premier 1.0: 35.4 (#176), Qwen3 32B: 40.0 (#112)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| MMLU-Pro | 72.6% | — |
| Vectara Hallucination Rate | — | 5.9% |
| GPQA (HELM) | 51.8% | — |
| LMArena Expert | — | 1362 |
Multilingual Not comparable
Nova Premier 1.0: —, Qwen3 32B: 45.8 (#162)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Qwen3 32B leads
Nova Premier 1.0: 66.9 (#201), Qwen3 32B: 69.1 (#174)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| IFEval | 80.3% | — |
| LMArena Instruction Following | — | 1305 |
Long Context Not comparable
Nova Premier 1.0: —, Qwen3 32B: 43.7 (#83)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |
Writing & Preference Qwen3 32B leads
Nova Premier 1.0: 51.0 (#174), Qwen3 32B: 53.1 (#158)
| Benchmark | Nova Premier 1.0 | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| WildBench | 78.8% | — |
| LMArena Multi-Turn | — | 1331 |
Frequently asked questions
Is Nova Premier 1.0 better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 37.7 on the Noometry Index.
Which is cheaper, Nova Premier 1.0 or Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 131K.
How many benchmarks do Nova Premier 1.0 and Qwen3 32B share?
1 benchmark has published results for both models. Nova Premier 1.0 has 6 scored results on Noometry and Qwen3 32B has 26.