Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1452 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multiple Choice Question Answering | Riddle (test) | 21 | Apr 21, 2026 | ||
| Multiple Choice Question Answering | OBQA (test) | 21 | Apr 21, 2026 | ||
| Multiple Choice Question Answering | ARC (test) | 21 | Apr 21, 2026 | ||
| Helpfulness | Helpfulness | 21 | Apr 21, 2026 | ||
| Harmlessness | Harmlessness | 21 | Apr 21, 2026 | ||
| Few-shot Indoor Scene Classification | Places8 (val) | 21 | Apr 21, 2026 | ||
| Camouflaged Object Detection | CAMO | 21 | May 18, 2026 | ||
| Mathematical Reasoning | MATH-500 | 21 | May 18, 2026 | ||
| Semi-supervised Tabular Classification | OpenML 11 (various) | 21 | Apr 21, 2026 | ||
| Visual Policy Reasoning | ClevrPolicy-M N=6 | 21 | Apr 21, 2026 | ||
| Safety Detection | chat 1m (test) | 21 | Apr 21, 2026 | ||
| Safety Detection | Harmbench (test) | 21 | Apr 21, 2026 | ||
| Video Question Answering | Video-MME v1.0 (test) | 21 | May 22, 2026 | ||
| Event Prediction | TAOBAO | 21 | Apr 20, 2026 | ||
| Visual Speech Recognition | DVSpeaker (Cross-scene) | 21 | Apr 20, 2026 | ||
| Visual Speech Recognition | DVSpeaker Matched-scene | 21 | Apr 20, 2026 | ||
| Graph Anomaly Detection | Disney | 21 | May 21, 2026 | ||
| Classification | DP Scaled Datasets 3x | 21 | Apr 20, 2026 | ||
| Classification | DP Scaled Datasets 2x | 21 | Apr 20, 2026 | ||
| General Benchmark Aggregation | Overall Evaluation Suite | 21 | Apr 20, 2026 | ||
| Reasoning | AGIEval English | 21 | Apr 20, 2026 | ||
| Agentic Search | MMSearch v1.0 (test) | 21 | Apr 16, 2026 | ||
| Cluster count selection | S3 | 21 | Apr 16, 2026 | ||
| Cluster count selection | S1 | 21 | Apr 16, 2026 | ||
| Multi-page Document Understanding | DUDE | 21 | Apr 16, 2026 |