Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2115 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-view Multimodal Reasoning | BLINK MV | 16 | Jun 23, 2026 | ||
| Forecasting Rejection | M3 Monthly (Source holdout) | 16 | Jun 23, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 16 | Jun 23, 2026 | ||
| Mathematical Reasoning | MATH 500 | 16 | Jun 23, 2026 | ||
| Node Classification | GraphLand Classification Aggregate | 16 | Jun 23, 2026 | ||
| Node Classification | tolokers RL 2 | 16 | Jun 23, 2026 | ||
| Node Classification | city-reviews RL | 16 | Jun 23, 2026 | ||
| Node Classification | artnet-exp (RL split) | 16 | Jun 23, 2026 | ||
| Single-robot SLAM | HERCULES Forest | 16 | Jun 23, 2026 | ||
| Single-robot SLAM | HERCULES Desert-Center | 16 | Jun 23, 2026 | ||
| Single-robot SLAM | HERCULES Desert-Perimeter | 16 | Jun 23, 2026 | ||
| Single-robot SLAM | HERCULES City | 16 | Jun 23, 2026 | ||
| Mathematical Reasoning | AIME 24 | 16 | Jun 23, 2026 | ||
| Multi-task Model Evaluation | AIME24, AIME25, HMMT25, HE+, MBPP+ Average | 16 | Jun 23, 2026 | ||
| Mathematical Problem Solving | HMMT25 | 16 | Jun 23, 2026 | ||
| Mathematical Problem Solving | AIME25 | 16 | Jun 23, 2026 | ||
| Mathematical Problem Solving | AIME 24 | 16 | Jun 23, 2026 | ||
| Enzyme Commission Prediction | Enzyme Commission | 16 | Jun 23, 2026 | ||
| BCVA forecasting | DME | 16 | Jun 23, 2026 | ||
| BCVA forecasting | nAMD | 16 | Jun 23, 2026 | ||
| Federated Continual Learning | ImageNet-R (20-split) | 16 | Jun 23, 2026 | ||
| Federated Continual Learning | ImageNet-R (10-split) | 16 | Jun 23, 2026 | ||
| Federated Continual Learning | ImageNet-R 5-split | 16 | Jun 23, 2026 | ||
| Graph Counterfactual Explanations | BA-2Motifs | 16 | Jun 23, 2026 | ||
| Medical Image Classification | BloodMNIST | 16 | Jun 23, 2026 |