Model comparison
Nova Premier 1.0 vs Qwen2.5-VL 72B Instruct
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 29.9 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 Qwen2.5-VL 72B Instruct in 0 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 44.8% for Nova Premier 1.0 and 36% for Qwen2.5-VL 72B Instruct.
- Qwen2.5-VL 72B Instruct is cheaper at $2.80 / $8.40 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.
- Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Nova Premier 1.0 | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 38.3 | 29.9 |
| Released | 2025-04-30 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 10K | 8K |
| Input $ / M tokens | $2.50 | $2.80 |
| Output $ / M tokens | $12.50 | $8.40 |
| Results tracked | 6 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Agentic & Tool Use Not comparable
Nova Premier 1.0: —, Qwen2.5-VL 72B Instruct: 18.6 (#144)
| Benchmark | Nova Premier 1.0 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning Nova Premier 1.0 leads
Nova Premier 1.0: 23.0 (#185), Qwen2.5-VL 72B Instruct: 20.7 (#233)
| Benchmark | Nova Premier 1.0 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 44.8% | 36% |
Math Not comparable
Nova Premier 1.0: 33.8 (#199), Qwen2.5-VL 72B Instruct: —
| Benchmark | Nova Premier 1.0 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Omni-MATH | 35% | — |
Knowledge Not comparable
Nova Premier 1.0: 35.8 (#180), Qwen2.5-VL 72B Instruct: —
| Benchmark | Nova Premier 1.0 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| MMLU-Pro | 72.6% | — |
| GPQA (HELM) | 51.8% | — |
Multimodal Not comparable
Nova Premier 1.0: —, Qwen2.5-VL 72B Instruct: 33.5 (#97)
| Benchmark | Nova Premier 1.0 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Instruction Following Not comparable
Nova Premier 1.0: 66.8 (#204), Qwen2.5-VL 72B Instruct: —
| Benchmark | Nova Premier 1.0 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| IFEval | 80.3% | — |
Writing & Preference Not comparable
Nova Premier 1.0: 51.0 (#178), Qwen2.5-VL 72B Instruct: —
| Benchmark | Nova Premier 1.0 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| WildBench | 78.8% | — |
Frequently asked questions
Is Nova Premier 1.0 better than Qwen2.5-VL 72B Instruct?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 29.9 on the Noometry Index.
Which is cheaper, Nova Premier 1.0 or Qwen2.5-VL 72B Instruct?
Qwen2.5-VL 72B Instruct is cheaper. It lists at $2.80 per million input tokens and $8.40 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 Qwen2.5-VL 72B Instruct share?
1 benchmark has published results for both models. Nova Premier 1.0 has 6 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.