Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1713 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|
| DeepSearchQA | DeepSearchQA | retrieval search ragnlp |
| 19 | Apr 14, 2026 |
|---|
| Murder Mystery Game Evaluation | Murder Mystery Games | llm chat instruction |
| 19 | Apr 14, 2026 |
|---|
| Action Recognition | GYM99 | computer vision |
| 19 | Apr 23, 2026 |
|---|
| Remote Sensing Perception and Reasoning | XLRS-Bench | computer vision |
| 19 | Apr 14, 2026 |
|---|
| Mathematical Reasoning | Minerva Math | llm chat instructionnlp |
| 19 | Apr 14, 2026 |
|---|
| Molecule Generation | Moses | bio medical |
| 19 | Apr 21, 2026 |
|---|
| Knowledge Graph Question Answering | WebQSP | graphnlp |
| 19 | Apr 14, 2026 |
|---|
| General GUI navigation | OS-Genesis | agents tool userobotics embodied ai |
| 19 | Apr 14, 2026 |
|---|
| E-commerce risk management multi-step trajectory evaluation | RISK-Bench Multi-step | agents tool useadversarial safety security |
| 19 | Apr 14, 2026 |
|---|
| E-commerce risk management single-step trajectory evaluation | RISK-Bench Single-step | agents tool useadversarial safety security |
| 19 | Apr 14, 2026 |
|---|
| Image Classification | STL-10 | computer vision |
| 19 | May 19, 2026 |
|---|
| Multimodal Generation | M2LONGBENCH (test) | multimodal |
| 19 | Apr 14, 2026 |
|---|
| Average Retrieval | DiDeMo (test) | retrieval search rag |
| 19 | Apr 14, 2026 |
|---|
| Audio-to-Text Retrieval | DiDeMo (test) | speech audioretrieval search rag |
| 19 | Apr 14, 2026 |
|---|
| Text-to-Audio Retrieval | DiDeMo (test) | multimodalnlp+1 |
| 19 | Apr 14, 2026 |
|---|
| Audio-to-Video Retrieval | DiDeMo (test) | multimodalspeech audio |
| 19 | Apr 14, 2026 |
|---|
| Video-to-Audio Retrieval | DiDeMo (test) | multimodalspeech audio |
| 19 | Apr 14, 2026 |
|---|
| Multimodal Retrieval | VGGSound-S (test) | retrieval search ragmultimodal |
| 19 | Apr 14, 2026 |
|---|
| Dynamic Facial Expression Recognition | FERV39K (test) | computer vision |
| 19 | Apr 14, 2026 |
|---|
| Human Activity Recognition | Parkinson | computer vision |
| 19 | Apr 14, 2026 |
|---|
| Human Activity Recognition | HAR70+ | computer vision |
| 19 | Apr 14, 2026 |
|---|
| Human Activity Recognition | HuGaDB | computer vision |
| 19 | Apr 14, 2026 |
|---|
| Human Activity Recognition | Daily-Sports | computer vision |
| 19 | Apr 14, 2026 |
|---|
| Human Activity Recognition | TNDA | computer vision |
| 19 | Apr 14, 2026 |
|---|
| Language Model Robustness under Adversarial Attack | MMLU Adversarially Perturbed | adversarial safety securityllm chat instruction |
| 19 | Apr 14, 2026 |
|---|