Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 992 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Functional Correctness | HumanEval | 27 | Jun 5, 2026 | ||
| Code Generation | HumanEval | 27 | Jun 5, 2026 | ||
| Skill-selection | ToolBench-60 one-hot preference regime (held-out pool) | 27 | Jun 5, 2026 | ||
| Multimodal Search | MAT-Search | 27 | Jun 5, 2026 | ||
| Multimodal Search | HR-MMSearch | 27 | Jun 5, 2026 | ||
| Image Denoising | Set12 Starfish (test) | 27 | Jun 5, 2026 | ||
| Image Denoising | Set12 Peppers (test) | 27 | Jun 5, 2026 | ||
| Image Classification | MNIST (train) | 27 | Jun 5, 2026 | ||
| Electricity consumption prediction | PG&E 50 users | 27 | Jun 5, 2026 | ||
| Electricity consumption prediction | PG&E dataset 50 users | 27 | Jun 5, 2026 | ||
| Electricity consumption prediction | PG&E dataset 50 users (test) | 27 | Jun 5, 2026 | ||
| XML Fuzzing | XML fuzzing benchmarks | 27 | Jun 4, 2026 | ||
| Code Agent Task | Terminal-Bench 2.0 | 27 | Jul 2, 2026 | ||
| Text-to-Speech | LibriSpeech-PC (test) | 27 | Jul 1, 2026 | ||
| Feature Matching | MegaDepth larger scale differences | 27 | Jun 4, 2026 | ||
| Model Stealing | AIDS | 27 | Jun 4, 2026 | ||
| Model Stealing | NCI109 | 27 | Jun 4, 2026 | ||
| Model Stealing | NCI1 | 27 | Jun 4, 2026 | ||
| Function approximation | Dimension 1 | 27 | Jun 4, 2026 | ||
| Overall Driving Performance | GEODRIVE-BENCH cross-country standard deviation | 27 | Jun 4, 2026 | ||
| Overall | GEODRIVE-BENCH | 27 | Jun 4, 2026 | ||
| Planning | GEODRIVE-BENCH | 27 | Jun 4, 2026 | ||
| Perception | GEODRIVE-BENCH | 27 | Jun 4, 2026 | ||
| Oblivious Transfer | OT protocols from literature | 27 | Jun 2, 2026 | ||
| Agent Safety Evaluation | AgentHarm Libra | 27 | Jun 2, 2026 |