Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2185 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Allocative Efficiency Prediction | Double Auction AE Round 1 (test) | 16 | Apr 21, 2026 | ||
| Competitive Equilibrium Price (CEP) Prediction | CEP Market Size Analysis (test) | 16 | Apr 21, 2026 | ||
| Aggregated Performance Evaluation | GQA, MME, POPE, MMStar, OCRBench, and ChartQA Aggregate | 16 | Apr 21, 2026 | ||
| Accuracy Prediction | LLM Compression Performance Accuracy | 16 | Apr 21, 2026 | ||
| Continuous Spatio-Temporal Video Super-Resolution | Adobe240 (test) | 16 | Apr 21, 2026 | ||
| Arbitrary Video Super-Resolution | Adobe240 105 (test) | 16 | Apr 21, 2026 | ||
| Arbitrary Video Super-Resolution | GoPro 85 (test) | 16 | Apr 21, 2026 | ||
| Agentic Search | BrowseComp | 16 | Apr 21, 2026 | ||
| Action Recognition | NTU RGB+D Average 120 | 16 | Apr 21, 2026 | ||
| Generative Modeling | 7-DOF Robot Arm | 16 | Apr 21, 2026 | ||
| Source-Free Domain Adaptation | DomainNet-126 Closed-set | 16 | Apr 21, 2026 | ||
| Mental Health Safety Evaluation | MHSafeEval seven mental-health harm categories 1.0 | 16 | Apr 21, 2026 | ||
| Safety Evaluation | HarmBench, TruthfulQA, and BBQ | 16 | Apr 21, 2026 | ||
| Automatic Speech Recognition | AfriSpeech-200 (target domains) | 16 | Apr 21, 2026 | ||
| Referring Expression Comprehension | VRSBench (test) | 16 | Apr 21, 2026 | ||
| Image Denoising | CBSD68 | 16 | Jun 23, 2026 | ||
| Multi-player game search | Threehex | 16 | Apr 21, 2026 | ||
| Multi-player game search | Triinversion | 16 | Apr 21, 2026 | ||
| Multi-player game search | 3 Player Hex | 16 | Apr 21, 2026 | ||
| Human Preference Alignment | HPS v2.1 | 16 | Apr 21, 2026 | ||
| Multi-dimensional cognitive state understanding | CognitiveBench Averaged across CUT, UE, and DEI (test) | 16 | Apr 21, 2026 | ||
| Uncertainty Estimation | QASPER | 16 | Apr 21, 2026 | ||
| Uncertainty Estimation | HotpotQA | 16 | Apr 21, 2026 | ||
| Uncertainty Estimation | AmbigQA | 16 | Apr 21, 2026 | ||
| Financial workflow task execution | RealFin benchmark | 16 | Jun 9, 2026 |