Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1536 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Watermark Detection | Code-Search-Net first 50k texts | 20 | Jun 18, 2026 | ||
| Video Understanding | 5 Video Benchmarks suite (MMVU, MVBench, VMME, VMMES, VMMMU) | 20 | Jun 17, 2026 | ||
| Language Model Reasoning and Knowledge Evaluation | 10 LLM Benchmarks suite (AIME25, AIME26, CEval, GPQA-D, HLE, IMO-AB, MMLU, MMLU-Pro, MMLU-Rd, MultiCh) | 20 | Jun 17, 2026 | ||
| Text-to-Image Generation | Z-Image | 20 | Jun 17, 2026 | ||
| Aesthetic Image Generation | Z-Image | 20 | Jun 17, 2026 | ||
| Countdown | Countdown 4 | 20 | Jun 17, 2026 | ||
| Time-series Forecasting | Weather | 20 | Jun 17, 2026 | ||
| Time-series Forecasting | ETTm2 | 20 | Jun 17, 2026 | ||
| Execution-based output prediction | CRUXEval-O 200-sample (seed 42) (test) | 20 | Jun 17, 2026 | ||
| Cybersecurity (CTF) | InterCode CTF | 20 | Jun 17, 2026 | ||
| State Abstraction | AMA-Bench SA | 20 | Jun 17, 2026 | ||
| State Updating | AMA-Bench (SU) | 20 | Jun 17, 2026 | ||
| Causal Inference | AMA-Bench (CI) | 20 | Jun 17, 2026 | ||
| Physics Reasoning | MemoryArena Physics | 20 | Jun 17, 2026 | ||
| Mathematical Reasoning | MemoryArena Math | 20 | Jun 17, 2026 | ||
| Uncertainty Quality Assessment | HCP brain dataset (test) | 20 | Jun 17, 2026 | ||
| Direction of Arrival Estimation | Simulated dataset | 20 | Jun 17, 2026 | ||
| Multi-hop QA | 2WikiMHQA Wiki18 index (test) | 20 | Jun 17, 2026 | ||
| Style Composition | Style Composition Benchmark (SCB) | 20 | Jun 17, 2026 | ||
| Super-res (4x) | ImageNet 256x256 | 20 | Jun 30, 2026 | ||
| Single-view metric depth estimation | OpenScene | 20 | Jul 8, 2026 | ||
| Single-view metric depth estimation | Waymo | 20 | Jul 8, 2026 | ||
| Image Classification | ImageNet (val) | 20 | Jun 16, 2026 | ||
| Image Classification | ImageNet 1k (test) | 20 | Jun 16, 2026 | ||
| Reading Comprehension | DROP | 20 | Jun 16, 2026 |