Neura Intelligence Index
| Benchmark | o1-mini | Qwen3 VL 4B Thinking |
|---|---|---|
| GPQA Diamond | 60 | 64.1 |
| Benchmark | o1-mini | Qwen3 VL 4B Thinking |
|---|---|---|
| AIME 2025 | — | 74.5 |
| Benchmark | o1-mini | Qwen3 VL 4B Thinking |
|---|---|---|
| MMMU-Pro | — | 57 |
| CharXiv Reasoning | — | 50.3 |
| ScreenSpot Pro | — | 49.2 |
| Benchmark | o1-mini | Qwen3 VL 4B Thinking |
|---|---|---|
| OSWorld | — | 31.4 |