Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2131 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reading Comprehension | DROP | 16 | Jun 11, 2026 | ||
| Code Generation | MBPP | 16 | Jun 11, 2026 | ||
| Mathematical Reasoning | MATH | 16 | Jun 11, 2026 | ||
| AI-generated Content Detection | LOKI out-of-distribution | 16 | Jun 11, 2026 | ||
| AI-generated Content Detection | FakeClue in-distribution | 16 | Jun 11, 2026 | ||
| Talking Head Generation | TalkVid self-driven 30 clips (held-out) | 16 | Jun 11, 2026 | ||
| Automatic Speech Recognition | SlideAVSR (test) | 16 | Jun 11, 2026 | ||
| Automatic Speech Recognition | SlideSpeech (test) | 16 | Jun 11, 2026 | ||
| Region Classification | OPT-RSVG (test) | 16 | Jun 11, 2026 | ||
| Region Captioning | OPT-RSVG (test) | 16 | Jun 11, 2026 | ||
| Complex Reasoning and Semantics | SO-Bench | 16 | Jun 11, 2026 | ||
| Spatial Relation Understanding | SO-Bench | 16 | Jun 11, 2026 | ||
| Basic Detection and Estimation | SO-Bench | 16 | Jun 11, 2026 | ||
| EEG-based emotion recognition | SEED | 16 | Jun 11, 2026 | ||
| EEG-based emotion recognition | BETA | 16 | Jun 11, 2026 | ||
| Time Series Forecasting | BS | 16 | Jun 11, 2026 | ||
| Time Series Forecasting | EDF | 16 | Jun 11, 2026 | ||
| Time Series Forecasting | EPF-BE | 16 | Jun 11, 2026 | ||
| Time Series Forecasting | EPF-PJM | 16 | Jun 11, 2026 | ||
| Multi-Doc QA | LongBench v2 (test) | 16 | Jun 11, 2026 | ||
| Multimodal Question Answering | WebQA Text-grounded n=2,455 (test) | 16 | Jun 11, 2026 | ||
| Multimodal Question Answering | WebQA Image-grounded n=2,511 (test) | 16 | Jun 11, 2026 | ||
| Text-based Question Answering | 2WikiMultihopQA & MuSiQue Out-of-domain Average (val) | 16 | Jun 11, 2026 | ||
| Text-based Question Answering | MuSiQue (val) | 16 | Jun 11, 2026 | ||
| Text-based Question Answering | 2WikiMultihopQA (val) | 16 | Jun 11, 2026 |