Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2519 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | ImageNet (test) | 15 | Feb 26, 2026 | ||
| Photo-Sketch Matching | PSC6K (test) | 15 | Feb 26, 2026 | ||
| Text-to-scene generation | 3D-FRONT Livingroom (test) | 15 | Jun 9, 2026 | ||
| 3D-Text Retrieval | Objaverse-LVIS 1.0 (test) | 15 | Feb 26, 2026 | ||
| 3D-Text Matching | Objaverse-LVIS 1.0 (test) | 15 | Feb 26, 2026 | ||
| Question Answering | M3SciQA | 15 | Mar 4, 2026 | ||
| Hallucination Detection | HaluEval | 15 | Apr 6, 2026 | ||
| Taxonomy Expansion | WordNet (test) | 15 | Feb 26, 2026 | ||
| Taxonomy Expansion | SemEval Food 2016 (test) | 15 | Feb 26, 2026 | ||
| Question Answering | HotpotQA | 15 | Feb 26, 2026 | ||
| Semantic Segmentation | ACDC v1 (test) | 15 | Feb 26, 2026 | ||
| Semantic Segmentation | FoggyCityscapes v1 (test) | 15 | Feb 26, 2026 | ||
| Overall Performance | Must-C & Spoken-SQuAD | 15 | Feb 26, 2026 | ||
| Spoken Question Answering | Spoken-SQuAD | 15 | Feb 26, 2026 | ||
| Speech Translation | Must-C | 15 | Feb 26, 2026 | ||
| Object presence hallucination evaluation | POPE GQA 2019 (Random) | 15 | Feb 26, 2026 | ||
| Object presence hallucination evaluation | POPE A-OKVQA Popular 2022 | 15 | Feb 26, 2026 | ||
| Real-time latency evaluation | AG-News | 15 | Feb 26, 2026 | ||
| Speech Translation | FLEURS (test) | 15 | Feb 26, 2026 | ||
| Phone Recognition | Seen Languages | 15 | Feb 26, 2026 | ||
| Recommendation | InstructRec Amazon Movietv (test) | 15 | Feb 26, 2026 | ||
| Web navigation | MiniWob++ | 15 | Feb 26, 2026 | ||
| Semantic Correspondence | AP-10K | 15 | May 29, 2026 | ||
| Mathematical Reasoning | ASDiv-Aug | 15 | Feb 26, 2026 | ||
| Continuation Zero-shot Speech Synthesis | LibriSpeech (test-clean) | 15 | Feb 26, 2026 |