Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1926 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Compositional Generalization | Evaluation Dataset (Unseen Average) | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset Seen Average | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset Unseen (Fold 3) | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset (Fold 3 Seen) | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset Unseen (Fold 2) | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset (Fold 2 Seen) | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset Unseen (Fold 1) | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset (Fold 1 Seen) | 18 | Feb 26, 2026 | ||
| Compositional Generalization | Evaluation Dataset (Full) | 18 | Feb 26, 2026 | ||
| Question Answering | PubMedQA | 18 | Feb 26, 2026 | ||
| Instruction following | General Domain AlpacaEval Arena-Hard LLaMA3-8B (10% selection) | 18 | Feb 26, 2026 | ||
| Math problem solving | Math Domain (AIME24, Math-OAI, Minerva, Olympiad, ACM23) Qwen2.5-7B (10% selection) | 18 | Feb 26, 2026 | ||
| Code Generation | Code Domain HumanEval, HumanEval+, MBPP, MBPP+, Bigcode (test) | 18 | Feb 26, 2026 | ||
| Molecular Captioning | MolReasoner original (test) | 18 | Feb 26, 2026 | ||
| Speech Reconstruction | Salmon Sentiment Consistency emotional 2025b (OOD) | 18 | Feb 26, 2026 | ||
| Video Preference Evaluation | ShareGPT-Video | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8k | 18 | Feb 26, 2026 | ||
| Code Generation | MBPP | 18 | Feb 26, 2026 | ||
| Reward Modeling | PPE-IFEval | 18 | Feb 26, 2026 | ||
| Prompt Classification | SEA-SafeguardBench English | 18 | Feb 26, 2026 | ||
| Multi-Hop Question Answering | HotpotQA (test val) | 18 | Jul 8, 2026 | ||
| Factual Knowledge Evaluation | Wikidata knowledge infusion | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 24 | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC23 | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH | 18 | Feb 26, 2026 |