Mixture-of-Experts
Reported on 2 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Methodology2 results
- Average Accuracy92.19best: 93.52 (Gumbel-Matrix Routing)
- Average Accuracy92.19best: 93.52 (Gumbel-Matrix Routing)