Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1651 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| ICDiff | D-Rep (test) | 20 | Feb 26, 2026 | ||
| Multimodal Understanding | SEED-Bench SEED-I | 20 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | MuJoCo walker2d medium-replay D4RL | 20 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | MuJoCo halfcheetah-medium-replay D4RL | 20 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | MuJoCo halfcheetah-medium D4RL | 20 | Feb 26, 2026 | ||
| Backdoor Defense | CIFAR-10 1.0 (test) | 20 | Feb 26, 2026 | ||
| Examination | CMMLU | 20 | Feb 26, 2026 | ||
| Examination | MMLU | 20 | Feb 26, 2026 | ||
| Understanding | C3 | 20 | Feb 26, 2026 | ||
| Understanding | XSum | 20 | Feb 26, 2026 | ||
| Understanding | RACE Middle | 20 | Feb 26, 2026 | ||
| Knowledge | CommonSenseQA CoQA | 20 | Feb 26, 2026 | ||
| Language | CHID | 20 | Feb 26, 2026 | ||
| Reasoning | CMNLI | 20 | Feb 26, 2026 | ||
| Runtime Prediction | K-SAT Random (test) | 20 | Feb 26, 2026 | ||
| Image Compression | Kodak | 20 | Feb 26, 2026 | ||
| Question Answering | TruthfulQA | 20 | Feb 26, 2026 | ||
| Information Retrieval | MS MARCO TREC DL19 1.0 (test) | 20 | Feb 26, 2026 | ||
| Video understanding | MVBench (val) | 20 | Feb 26, 2026 | ||
| Visual reasoning | NLVR2 (val) | 20 | Feb 26, 2026 | ||
| Sequential Recommendation | Clothing | 20 | Jun 23, 2026 | ||
| Confounding Detection | Erdös-Rényi Causal Graphs Setting 3 Synthetic | 20 | Feb 26, 2026 | ||
| Confounding Detection | Erdös-Rényi Causal Graphs Setting 2 Synthetic | 20 | Feb 26, 2026 | ||
| Confounding Detection | Erdös-Rényi Causal Graphs Setting 1 Synthetic | 20 | Feb 26, 2026 | ||
| Intent Classification | BANKING77 5-shot (test) | 20 | Feb 26, 2026 |