Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1698 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Web Navigation | WebArena Lite v2 | 19 | May 27, 2026 | ||
| Summarization | XSum | 19 | May 27, 2026 | ||
| Mathematical Reasoning | GSM8K | 19 | May 27, 2026 | ||
| Code Generation | HumanEval | 19 | May 27, 2026 | ||
| Summarization | CNN/DM | 19 | May 27, 2026 | ||
| Text Generation | ShareGPT | 19 | May 27, 2026 | ||
| Language Modeling | WikiText-2 | 19 | May 26, 2026 | ||
| Image Classification | SUN397 | 19 | Jun 5, 2026 | ||
| Speech Coding | LibriTTS 16 kHz (test) | 19 | May 27, 2026 | ||
| Multi-image spatial reasoning | SPBench-MV | 19 | May 26, 2026 | ||
| Perspective-dependent reasoning | ViewSpatial-Bench | 19 | May 26, 2026 | ||
| Out-of-distribution detection | OOD Detection Source LLM GPT-4o (test) | 19 | May 26, 2026 | ||
| Out-of-distribution detection | OOD Detection Source LLM: Claude-3.5-Haiku (test) | 19 | May 26, 2026 | ||
| Out-of-distribution detection | OOD Detection Source LLM: Gemini-2.5-Flash (test) | 19 | May 26, 2026 | ||
| Text-intensive Visual Question Answering | VQAText | 19 | Jun 2, 2026 | ||
| Multimodal Understanding | MMT | 19 | Jul 1, 2026 | ||
| Medical Time Series Classification | ADFTD (subject-independent) | 19 | May 26, 2026 | ||
| Competitive Programming | ICPC-Eval | 19 | May 26, 2026 | ||
| Competitive Programming | LiveCodeBench Pro 2025Q2 | 19 | May 26, 2026 | ||
| Long-horizon agent performance | BrowseComp | 19 | May 26, 2026 | ||
| Offline Reinforcement Learning | D4RL walker2d-medium-expert-sparse | 19 | May 26, 2026 | ||
| Offline Reinforcement Learning | D4RL hopper-medium-expert-sparse | 19 | May 26, 2026 | ||
| Offline Reinforcement Learning | D4RL halfcheetah-medium-expert-sparse | 19 | May 26, 2026 | ||
| Downstream task evaluation | LM Evaluation Harness MMLU, ARC, HellaSwag, TruthfulQA, Winogrande, CommonsenseQA | 19 | May 26, 2026 | ||
| Individual Treatment Effect Estimation | Blog (test) | 19 | May 26, 2026 |