Aggregated
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multitask LLM Evaluation | Aggregated MMLU, GSM8K, HumanEval | Average Accuracy88.33 | 42 | |
| General Language Evaluation | Aggregated MMLU, BoolQ, OpenBookQA, RTE | Average Accuracy70.4 | 42 | |
| Video understanding | Aggregated Average Score | Average Score62.7 | 36 | |
| Classification | Aggregated | Accuracy71.44 | 28 | |
| Feature Selection | Aggregated AL, CH, CO, EY, GE, HE, HI, HO, JA, MI, OT, YE | Rank2.17 | 17 | |
| Overall Performance | Aggregated All Benchmarks | Average Score40.3 | 12 | |
| General Language Proficiency | Aggregated GSM8K, TruthfulQA, TriviaQA, CNN/DM, MMLU | Average Score48.6 | 9 | |
| General Performance | Aggregated MMLU, HellaSwag, TruthfulQA, GSM8K, MATH, MBPP, HumanEval | Average Score40.35 | 9 | |
| Context Compression for Question Answering | Aggregated NQ, TQA, HQA, 2Wiki, Musique | EM34 | 8 | |
| Disentanglement | Aggregated | InfoM0.76 | 8 | |
| Selective Prediction | Aggregated Univariate, 1D, and 2D regression tasks (test) | SSE1.78 | 5 | |
| Disentanglement | Aggregated (Shapes3D, MPI3D, Falcor3D, Isaac3D) | InfoM Score0.65 | 5 | |
| General Reasoning Efficiency | Aggregated (Sudoku, Maze, ARC, DDE) | Fp Score3.04 | 4 | |
| Faithfulness Diagnosticity | Aggregated SST, Ev.Inf, AG, and M.RC | Alpha Score0.525 | 4 | |
| Instance-level search | Aggregated Mean All & Mean R1M (test) | Mean All0.601 | 2 |
Showing 15 of 15 rows