Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Kimi K3.1 Pro | Sora |
|---|---|---|
| GPQA Diamond | 94.2 | — |
| Humanity's Last Exam | 51.1 | — |
multimodal
| Benchmark | Kimi K3.1 Pro | Sora |
|---|---|---|
| MMMU-Pro | 84.1 | — |
| CharXiv Reasoning | 89 | — |
agent
| Benchmark | Kimi K3.1 Pro | Sora |
|---|---|---|
| BrowseComp | 92.1 | — |
| APEX Agents | 67.2 | — |
video_quality
| Benchmark | Kimi K3.1 Pro | Sora |
|---|---|---|
| VBench | — | 82.4 |
| Video Arena Elo | — | 1280 |
Category Winners
reasoning
M
Kimi K3.1 Pro88.4
multimodal
M
Kimi K3.1 Pro85.4
agent
M
Kimi K3.1 Pro94.3