Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2672 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|
| Multimodal Question Answering | World History | multimodalnlp+1 |
| 14 | Apr 21, 2026 |
|---|
| Burgers' Equation | PDEBench | miscellaneous |
| 14 | Apr 21, 2026 |
|---|
| 1D Diffusion-Sorption | PDEBench | miscellaneous |
| 14 | Apr 21, 2026 |
|---|
| 1D Diffusion-Reaction | PDEBench | miscellaneous |
| 14 | Apr 21, 2026 |
|---|
| Commonsense Plausibility Estimation (Free-form Text) | CFC | nlpllm chat instruction |
| 14 | Apr 21, 2026 |
|---|
| Uncertainty-guided selective generation | TriviaQA (val) | llm chat instructionnlp |
| 14 | Apr 21, 2026 |
|---|
| Hallucination Detection | TriviaQA (val) | llm chat instructionnlp |
| 14 | Apr 21, 2026 |
|---|
| Uncertainty-guided selective generation | CoQA (dev) | llm chat instructionnlp |
| 14 | Apr 21, 2026 |
|---|
| Hallucination Detection | CoQA (dev) | llm chat instructionnlp |
| 14 | Apr 21, 2026 |
|---|
| Offline Goal-Conditioned Reinforcement Learning | humanoidmaze large-navigate v0 | robotics embodied ai |
| 14 | May 21, 2026 |
|---|
| Offline Goal-Conditioned Reinforcement Learning | antmaze medium-navigate v0 | robotics embodied ai |
| 14 | Apr 21, 2026 |
|---|
| Political and Legal Affairs Assessment | PoliLegal | nlp |
| 14 | Apr 21, 2026 |
|---|
| Counterfactual Explanation | Moons 5-fold synthetic (test) | computer visionnlp |
| 14 | Apr 21, 2026 |
|---|
| Multi-hop Question Answering | MuSiQue | nlpretrieval search rag |
| 14 | Apr 21, 2026 |
|---|
| Multi-hop Question Answering | HotpotQA | nlpretrieval search rag |
| 14 | Apr 21, 2026 |
|---|
| Grounded Multimodal Entity Recognition | Twitter-FMNERG (test) | multimodalnlp+1 |
| 14 | Apr 21, 2026 |
|---|
| Safety Assessment | Safety Avg. | adversarial safety security |
| 14 | Apr 21, 2026 |
|---|
| Prosocial Safety Assessment | Prosocial | adversarial safety securityllm chat instruction |
| 14 | Apr 21, 2026 |
|---|
| Helpful and Harmless Response Generation | PKU-SafeRLHF alpaca2-7b (test) | llm chat instructionadversarial safety security |
| 14 | Apr 21, 2026 |
|---|
| Mathematical Reasoning | Average GSM8K, MATH-500, AMC23 | llm chat instructionnlp |
| 14 | Apr 21, 2026 |
|---|
| Mathematical Reasoning | MATH 500 | llm chat instructionnlp |
| 14 | Apr 21, 2026 |
|---|
| Mathematical Reasoning | GSM8K | llm chat instructionnlp |
| 14 | Apr 21, 2026 |
|---|
| Professional Multimodal Understanding | MMMU-Pro | multimodalcomputer vision+1 |
| 14 | Apr 21, 2026 |
|---|
| Science Question Answering | ScienceQA | nlpbio medical |
| 14 | Apr 21, 2026 |
|---|
| Multimodal Consistency Evaluation | ConBench | multimodalcomputer vision+1 |
| 14 | Apr 21, 2026 |
|---|