Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1068 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero-shot Reasoning | MathQA | 26 | Apr 3, 2026 | ||
| Zero-shot Reasoning | OpenbookQA | 26 | Apr 3, 2026 | ||
| Code Generation | CodeContests | 26 | Feb 26, 2026 | ||
| Projection onto the probability simplex | Probability Simplex | 26 | Feb 26, 2026 | ||
| Visual Question Answering | MMMU-Pro | 26 | May 22, 2026 | ||
| Temporal Knowledge Graph Question Answering | MultiTQ (test) | 26 | Mar 4, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 26 | Feb 27, 2026 | ||
| Event Mention Identification | M2E2 text-only | 26 | Mar 10, 2026 | ||
| Function Calling | Berkeley Function Call Leaderboard (BFCL) Live (Out-of-Domain) | 26 | Feb 26, 2026 | ||
| Function Calling | Berkeley Function Call Leaderboard (BFCL) Non-Live Out-of-Domain | 26 | Feb 26, 2026 | ||
| Closed-ended Visual Question Answering | LLS48-VQA | 26 | Feb 26, 2026 | ||
| Closed-ended Visual Question Answering | PitVQA | 26 | Feb 26, 2026 | ||
| Skill assessment | Cholec80 CVS | 26 | Feb 26, 2026 | ||
| Open-ended Visual Question Answering | LLS48-VQA | 26 | Feb 26, 2026 | ||
| Semantic Segmentation | GraSP | 26 | Feb 26, 2026 | ||
| Semantic Segmentation | DSAD | 26 | Feb 26, 2026 | ||
| Semantic Segmentation | CholecSeg8k | 26 | Feb 26, 2026 | ||
| Instance Segmentation | GraSP | 26 | Feb 26, 2026 | ||
| Object Detection | GraSP | 26 | Feb 26, 2026 | ||
| Code Generation | LiveCodeBench (LCB) V6 | 26 | Jul 7, 2026 | ||
| Counting | Pixmo (test) | 26 | Jun 9, 2026 | ||
| Counting | Pixmo (val) | 26 | Jun 9, 2026 | ||
| Natural Language Inference | LogicNLI | 26 | Feb 26, 2026 | ||
| Natural Language Inference | FOLIO | 26 | Feb 26, 2026 | ||
| NL-to-FOL Syntax Correctness | LogicNLI (test) | 26 | Feb 26, 2026 |