Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1847 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Climate Discovery | ClimaBench 2000–2024 | 18 | Apr 21, 2026 | ||
| Medical Image Classification | VinDr-PCXR | 18 | Apr 21, 2026 | ||
| Medical Image Classification | Derma | 18 | Apr 21, 2026 | ||
| Long-form Writing | LongBench-Write | 18 | Apr 21, 2026 | ||
| Long-form Writing | Creative-W.B. | 18 | Apr 21, 2026 | ||
| Long-form Writing | WritingBench | 18 | Apr 21, 2026 | ||
| Image Classification | ImageNet-C | 18 | Apr 21, 2026 | ||
| Multimodal Mathematical Reasoning | FlowVerse Vision Primary | 18 | Apr 21, 2026 | ||
| Multimodal Mathematical Reasoning | FlowVerse Vision Centric | 18 | Apr 21, 2026 | ||
| Multimodal Mathematical Reasoning | FlowVerse Vision Dense | 18 | Apr 21, 2026 | ||
| Multimodal Mathematical Reasoning | FlowVerse Text Limited | 18 | Apr 21, 2026 | ||
| Multimodal Mathematical Reasoning | FlowVerse All | 18 | Apr 21, 2026 | ||
| Camouflaged Object Detection | CAMO (test) | 18 | Apr 21, 2026 | ||
| Long-term time series forecasting | ETTh1 Average | 18 | May 19, 2026 | ||
| Question Answering | HotpotQA (full-slice) | 18 | Apr 21, 2026 | ||
| Question Answering | NQ-open Augmented (full-slice) | 18 | Apr 21, 2026 | ||
| Question Answering | NQ (val) | 18 | Apr 21, 2026 | ||
| Question Answering | Hotpots | 18 | Apr 21, 2026 | ||
| Question Answering | Hotpotd | 18 | Apr 21, 2026 | ||
| Question Answering | NQ SYNTH | 18 | Apr 21, 2026 | ||
| Question Answering | Helpful | 18 | Apr 21, 2026 | ||
| Question Answering | Distractor hard | 18 | Apr 21, 2026 | ||
| Question Answering | Restate hard | 18 | Apr 21, 2026 | ||
| Long-form Question Answering | ExpertQA | 18 | Apr 21, 2026 | ||
| Dialogue Summarization | ToFuEval | 18 | Apr 21, 2026 |