Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2193 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text-to-Video Generation | CountBench | 16 | Apr 10, 2026 | ||
| Text-to-Image Generation | GENEVAL | 16 | Apr 10, 2026 | ||
| Multi-task Evaluation | Fairness and Utility Suite | 16 | Apr 10, 2026 | ||
| Fairness Evaluation | CEB-Jigsaw | 16 | Apr 10, 2026 | ||
| Fairness Evaluation | CEB-Credit | 16 | Apr 10, 2026 | ||
| Fairness Evaluation | CEB Adult | 16 | Apr 10, 2026 | ||
| Object Goal Navigation | CHORES-S 1.0 (test) | 16 | Apr 10, 2026 | ||
| Multi-Agent Continuous Control | MA-MuJoCo 6Halfcheetah-Medium | 16 | Apr 10, 2026 | ||
| Abdominal Organ Segmentation | FLARE 22 (test) | 16 | May 13, 2026 | ||
| Long Video Understanding | LongVideoBench 473s | 16 | Apr 10, 2026 | ||
| Solving linear systems from discretized diffusion equations | Discretized diffusion equations 1000 realizations | 16 | Apr 10, 2026 | ||
| Zero-shot Evaluation | Downstream tasks average | 16 | Apr 10, 2026 | ||
| Output Length Prediction | LMSYS-Chat-1M (test) | 16 | Apr 10, 2026 | ||
| Output Length Prediction | LongBench (test) | 16 | Apr 10, 2026 | ||
| Output Length Prediction | MBPP (test) | 16 | Apr 10, 2026 | ||
| Output Length Prediction | GSM8K (test) | 16 | Apr 10, 2026 | ||
| Multi-agent steering | Synthetic Multi-agent Scenarios | 16 | Apr 10, 2026 | ||
| General Reasoning and Coding | Out-of-Distribution (ARC-c, GPQA, MMLU-Pro, LiveCodeBench) | 16 | Apr 10, 2026 | ||
| Personalized Recommendation | RecBench+ Book | 16 | Apr 10, 2026 | ||
| Personalized Recommendation | RecBench+ Movie | 16 | Apr 10, 2026 | ||
| Open-Ended Video Game Glitch Detection | VideoGlitchBench | 16 | Apr 10, 2026 | ||
| Code Hallucination Detection | BigCode | 16 | Apr 10, 2026 | ||
| Code Hallucination Detection | Odex | 16 | Apr 10, 2026 | ||
| Code Hallucination Detection | DS-1000 | 16 | Apr 10, 2026 | ||
| Reward Modeling | RewardBench 1k | 16 | Apr 10, 2026 |