Model comparison
Nova Premier 1.0 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 38.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 33.8.
- Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
Side by side
| Nova Premier 1.0 | Qwen3.8 Max | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 38.3 | 56.8 |
| Released | 2025-04-30 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 10K | 131K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $12.50 | $6 |
| Results tracked | 6 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nova Premier 1.0: —, Qwen3.8 Max: 53.5 (#29)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| LMArena Coding | — | 1502 |
Agentic & Tool Use Not comparable
Nova Premier 1.0: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Nova Premier 1.0: 23.0 (#185), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| Kagi LLM Benchmark | 44.8% | — |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
Nova Premier 1.0: 33.8 (#199), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| Omni-MATH | 35% | — |
| LMArena Math | — | 1499 |
Knowledge Qwen3.8 Max leads
Nova Premier 1.0: 35.8 (#180), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 72.6% | — |
| GPQA (HELM) | 51.8% | — |
| LMArena Expert | — | 1507 |
Multimodal Not comparable
Nova Premier 1.0: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Nova Premier 1.0: —, Qwen3.8 Max: 56.7 (#18)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1472 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Russian | — | 1481 |
| LMArena Spanish | — | 1492 |
Instruction Following Qwen3.8 Max leads
Nova Premier 1.0: 66.8 (#204), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| IFEval | 80.3% | — |
| LMArena Instruction Following | — | 1479 |
Long Context Not comparable
Nova Premier 1.0: —, Qwen3.8 Max: 45.6 (#31)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |
Writing & Preference Qwen3.8 Max leads
Nova Premier 1.0: 51.0 (#178), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Nova Premier 1.0 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| WildBench | 78.8% | — |
| LMArena Multi-Turn | — | 1489 |
Frequently asked questions
Is Nova Premier 1.0 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 38.3 on the Noometry Index.
Which is cheaper, Nova Premier 1.0 or Qwen3.8 Max?
Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Nova Premier 1.0 and Qwen3.8 Max share?
0 benchmarks have published results for both models. Nova Premier 1.0 has 6 scored results on Noometry and Qwen3.8 Max has 39.