Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1810 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Load forecasting | London Household Electricity (val) | 18 | Jun 2, 2026 | ||
| Forecasting | ComStock (val) | 18 | Jun 2, 2026 | ||
| Zero-shot Language Understanding | LM Evaluation Harness Downstream Suite (HellaSwag, PIQA, WinoGrande, OpenBookQA, SIQA, BoolQ, TriviaQA, MMLU, ARC-Challenge, ARC-Easy, MathQA, SciQ) | 18 | Jun 2, 2026 | ||
| Low-level vision quality assessment (Overall) | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Underwater Enhancement Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Super Resolution Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Shadow Removal Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Raindrop Removal Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Motion Deblurring Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Low-Light Enhancement Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| HDR Enhancement Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Desnowing Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Deraining Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Denoising Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Dehazing Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Defocus Deblurring Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Compression Artifacts Removal Quality Assessment | LL-Bench (test) | 18 | Jun 2, 2026 | ||
| Question Answering | HotpotQA (held-out) | 18 | Jun 2, 2026 | ||
| Question Answering | 2WikiMultiHopQA (held-out) | 18 | Jun 2, 2026 | ||
| Code Generation | CodeEval-Pro BigCodeBench-Lite-Pro and HumanEval-Pro (Held-out) | 18 | Jun 2, 2026 | ||
| Code Generation | CodeEval-Pro BigCodeBench-Lite-Pro and HumanEval-Pro (2nd Pass) | 18 | Jun 2, 2026 | ||
| Code Generation | CodeEval-Pro BigCodeBench-Lite-Pro and HumanEval-Pro (1st Pass) | 18 | Jun 2, 2026 | ||
| Semantic Segmentation | ARAS400k | 18 | Jun 2, 2026 | ||
| Overall Performance | MMG2Skill-Bench Average | 18 | Jun 2, 2026 | ||
| Strategic Decision Making | MMG2Skill-Bench Strategy | 18 | Jun 2, 2026 |