Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2152 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Abusive clause detection | Chilean Terms of Service Abusive domain | 16 | May 26, 2026 | ||
| Temporal Grounding | QVHighlights | 16 | Jun 11, 2026 | ||
| Electric Consumption Profile Distribution Modeling | Residential ECP 15-minute resolution (target domain) | 16 | May 26, 2026 | ||
| Electric Consumption Profile Distribution Modeling | Residential ECP 30-minute resolution (target domain) | 16 | May 26, 2026 | ||
| Electric Consumption Profile Distribution Modeling | Residential ECP 60-minute resolution (target domain) | 16 | May 26, 2026 | ||
| Temporal Sentence Grounding | ActivityNet Captions v1.3 (test) | 16 | Jun 1, 2026 | ||
| Multi-Domain Task-Incremental Learning (Transfer) | Multi-Domain Task-Incremental Learning Sequence (Aircraft, Caltech101, CIFAR100, DTD, Flowers, Food, StanfordCars, SUN397) 16-shot (test) | 16 | May 26, 2026 | ||
| Reward Model Transfer | UltraFeedback (UF) | 16 | May 26, 2026 | ||
| Reward Model Transfer | Anthropic Helpful (AH) | 16 | May 26, 2026 | ||
| Reward Model Transfer | HelpSteer3 (H3) v1 (test) | 16 | May 26, 2026 | ||
| General Language Modeling | CodaSet OOD Average (test) | 16 | May 26, 2026 | ||
| Multi-turn Dialogue Evaluation | MT_Bench CodaSet OOD (test) | 16 | May 26, 2026 | ||
| Code Generation | MBPP CodaSet OOD (test) | 16 | May 26, 2026 | ||
| Mathematical Reasoning | Math_500 CodaSet OOD (test) | 16 | May 26, 2026 | ||
| Holistic Evaluation | CodaSet ID Average (test) | 16 | May 26, 2026 | ||
| Instruction Following | CodaSet ID IFEVAL (test) | 16 | May 26, 2026 | ||
| Symbolic and Logical Reasoning | CodaSet BBH ID (test) | 16 | May 26, 2026 | ||
| Multi-discipline Knowledge Evaluation | CodaSet ID MMLU-PRO (test) | 16 | May 26, 2026 | ||
| Mathematical Reasoning | CodaSet ID GSM8k (test) | 16 | May 26, 2026 | ||
| Safety evaluation | Beaver | 16 | May 26, 2026 | ||
| Code reasoning | LCB v5 | 16 | May 26, 2026 | ||
| Imitation Learning | D4RL Ant | 16 | May 26, 2026 | ||
| Imitation Learning | D4RL Walker2d | 16 | May 26, 2026 | ||
| Imitation Learning | D4RL Halfcheetah | 16 | May 26, 2026 | ||
| Imitation Learning | D4RL Hopper | 16 | May 26, 2026 |