Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | GPT-4 | Qwen2-VL-72B-Instruct |
|---|---|---|
| GPQA Diamond | 35.7 | — |
multimodal
| Benchmark | GPT-4 | Qwen2-VL-72B-Instruct |
|---|---|---|
| MMMU-Pro | — | 46.2 |
Category Winners
reasoning
5.5
multimodal
Q
Qwen2-VL-72B-Instruct6.0