Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Qwen3 VL 32B Thinking | Runway Gen-3 Alpha |
|---|---|---|
| GPQA Diamond | 73.1 | — |
math
| Benchmark | Qwen3 VL 32B Thinking | Runway Gen-3 Alpha |
|---|---|---|
| AIME 2025 | 83.7 | — |
multimodal
| Benchmark | Qwen3 VL 32B Thinking | Runway Gen-3 Alpha |
|---|---|---|
| MMMU-Pro | 68.1 | — |
| CharXiv Reasoning | 65.2 | — |
| ScreenSpot Pro | 57.1 | — |
general
| Benchmark | Qwen3 VL 32B Thinking | Runway Gen-3 Alpha |
|---|---|---|
| SimpleQA | 55.4 | — |
agent
| Benchmark | Qwen3 VL 32B Thinking | Runway Gen-3 Alpha |
|---|---|---|
| OSWorld | 41 | — |
video_quality
| Benchmark | Qwen3 VL 32B Thinking | Runway Gen-3 Alpha |
|---|---|---|
| Video Arena Elo | — | 1210 |
| VBench | — | 80.2 |
Category Winners
math
Q
Qwen3 VL 32B Thinking58.7
reasoning
Q
Qwen3 VL 32B Thinking60.8
general
Q
Qwen3 VL 32B Thinking75.1
multimodal
Q
Qwen3 VL 32B Thinking35.5
agent
Q
Qwen3 VL 32B Thinking40.8