Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1748 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Knapsack Problem | KP N=200, W=25 | 19 | Feb 26, 2026 | ||
| Knapsack Problem | KP N=100, W=25 | 19 | Feb 26, 2026 | ||
| Knapsack Problem | KP N=50, W=12.5 | 19 | Feb 26, 2026 | ||
| Question Answering | Average 10K context | 19 | Feb 27, 2026 | ||
| Question Answering | NQ 10K context | 19 | Feb 27, 2026 | ||
| Question Answering | 2Wiki 30K context | 19 | Feb 27, 2026 | ||
| Question Answering | 2Wiki 10K context | 19 | Feb 27, 2026 | ||
| Question Answering | HotpotQA 10K context | 19 | Feb 27, 2026 | ||
| Multi-Armed Bandit | Bandit | 19 | Feb 26, 2026 | ||
| General AI Assistant | GAIA text | 19 | Feb 26, 2026 | ||
| Question Answering | HotpotQA (val) | 19 | May 27, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 19 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 19 | Feb 26, 2026 | ||
| Full Trajectory Prediction | EHRWorld-110K (test) | 19 | Feb 26, 2026 | ||
| Hyper-Relational Link Prediction | WD20K66 V2 | 19 | Feb 26, 2026 | ||
| Hyper-Relational Link Prediction | WD20K100 V2 | 19 | Feb 26, 2026 | ||
| Hyper-Relational Link Prediction | WD20K33 V1 | 19 | Feb 26, 2026 | ||
| Hyper-Relational Link Prediction | WD20K66 V1 | 19 | Feb 26, 2026 | ||
| Explanation Generation | Amazon Beauty (test) | 19 | Jun 30, 2026 | ||
| Agent Capability Evaluation | SEAL 0 | 19 | Apr 23, 2026 | ||
| Knowledge-based reasoning | RCW | 19 | Feb 26, 2026 | ||
| Knowledge-based reasoning | EMG | 19 | Feb 26, 2026 | ||
| Knowledge-based reasoning | ECG | 19 | Feb 26, 2026 | ||
| Knowledge-based reasoning | CTU | 19 | Feb 26, 2026 | ||
| Masked Entity Prediction | GDELT standard (test) | 19 | Feb 26, 2026 |