Overall Average
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Image Retrieval | Overall Average | mAP60.6 | 21 | |
| Creative Writing | Overall Average Poem, Joke, Story | Semantic Diversity0.3603 | 20 | |
| Depth Completion | Overall Average (ScanNet, IBims-1, VOID, NYUv2, KITTI, DDAD) | Rank1.75 | 17 | |
| Question Answering | Overall Average | Accuracy55 | 14 | |
| Open-Vocabulary Semantic Segmentation | Overall Average 9 datasets | Average IoU46.9 | 10 | |
| Mathematical Reasoning | Overall Average AIME MATH500 AMC23 | Majority Score (Avg)75.2 | 8 | |
| Aggregated Reasoning Evaluation | Overall Average | Average Score @ 1645.6 | 8 | |
| Synthetic Face Detection | Overall Average | Accuracy96.4 | 7 | |
| Image-Goal Navigation | Overall Average | SR50.2 | 6 | |
| Automatic Subtitling | Overall Average across MSTCIN, ECSC, and EPI (test) | Subtitling Error Rate (AVG)59.2 | 6 | |
| Point-Goal Navigation | Overall Average | SR80.4 | 5 | |
| Meta-evaluation | Overall Average | Accuracy Improvement9.7 | 5 | |
| Mathematical Reasoning | Overall Average | Avg Rank1.52 | 5 | |
| Aggregate Performance | Overall Average | Speedup4.12 | 4 | |
| Cross-domain Heuristic Design | Overall Average CVRP-C, TSP-ACO, OP-ACO, OVRP-C | Gap (%)32.85 | 4 | |
| fMRI-to-image reconstruction | Overall Average NSD, HCP, BOLD5000, NOD | PixCorr0.104 | 4 |
Showing 16 of 16 rows