Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2149 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | PANGAEA Aggregate | 16 | May 28, 2026 | ||
| Semantic Segmentation | CropTypeSS | 16 | May 28, 2026 | ||
| Semantic Segmentation | BurnSr | 16 | May 28, 2026 | ||
| Manipulation | scene-play v0 | 16 | Jun 4, 2026 | ||
| Comprehensive Evaluation | Overall Across Benchmarks | 16 | May 28, 2026 | ||
| Instruction | IFEval | 16 | May 28, 2026 | ||
| Multi-Task | GPQA | 16 | May 28, 2026 | ||
| Mathematics | AMC 24 | 16 | May 28, 2026 | ||
| Mathematics | AMC 23 | 16 | May 28, 2026 | ||
| Mathematics | MATH 500 | 16 | May 28, 2026 | ||
| Risk Indication | Sampled (test) | 16 | May 28, 2026 | ||
| Geometric Reasoning | Geo3K | 16 | Jun 23, 2026 | ||
| Grounded Reasoning | MM-GCoT | 16 | May 29, 2026 | ||
| Machine-generated text detection | TELL benchmark (test) | 16 | May 28, 2026 | ||
| AI Text Detection | Unified RL corpus (test) | 16 | May 28, 2026 | ||
| Move Prediction | LGB first 10 plies excluded Prompt-conditioned (test) | 16 | May 28, 2026 | ||
| Move Prediction | LIF-T10 first 10 plies excluded Prompt-conditioned (test) | 16 | May 28, 2026 | ||
| Move Prediction | LIF Prompt-conditioned first 10 plies excluded (test) | 16 | May 28, 2026 | ||
| Move Prediction | LIF-D Prompt-conditioned first 10 plies excluded (test) | 16 | May 28, 2026 | ||
| Move Prediction | Prompt-conditioned benchmarks Lichess (test) | 16 | May 28, 2026 | ||
| Policy-refinement | ToolEmu | 16 | May 28, 2026 | ||
| Output-refinement | Tweet Engagement | 16 | May 28, 2026 | ||
| Text-to-video generation | VBench | 16 | May 27, 2026 | ||
| Code Generation | LiveCodeBench v6 (test) | 16 | May 27, 2026 | ||
| Deep Research Evaluation | Deep Research Bench (step 1100) | 16 | May 27, 2026 |