Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2276 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-Hop QA Verification | HotpotQA | 16 | Feb 26, 2026 | ||
| Text Classification | QQP | 16 | Feb 26, 2026 | ||
| Text Classification | SST-2 | 16 | Feb 26, 2026 | ||
| Scientific Reasoning | GPQA | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | Olympiad | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 16 | Feb 26, 2026 | ||
| Arithmetic | Calc. | 16 | Feb 26, 2026 | ||
| Open-book generation under knowledge conflict | ConFiQA MR 1,500 | 16 | Feb 26, 2026 | ||
| Classification | MAMI | 16 | Feb 26, 2026 | ||
| Classification | FHM | 16 | Feb 26, 2026 | ||
| Response Generation | HiCUPID | 16 | Feb 26, 2026 | ||
| Response Selection | P-Soups Expertise | 16 | Feb 26, 2026 | ||
| Response Selection | P-Soups Style | 16 | Feb 26, 2026 | ||
| Response Selection | P-Soups Informativeness | 16 | Feb 26, 2026 | ||
| Response Selection | PersonaMem | 16 | Feb 26, 2026 | ||
| Response Selection | AlignX | 16 | Feb 26, 2026 | ||
| Recommendation | Amazon | 16 | Feb 26, 2026 | ||
| Recommendation | MIND | 16 | Feb 26, 2026 | ||
| Retrieval | MTEB-E English v2 | 16 | Feb 26, 2026 | ||
| High-Resolution Visual Reasoning | HRBench | 16 | Feb 26, 2026 | ||
| General Language Understanding | KMMLU | 16 | Jun 8, 2026 | ||
| Natural Language Understanding | Multiple Natural Language Benchmarks (Winogrande, PIQA, WSC, WNLI, SST-2, RTE, QNLI, CB, ARC-e, ARC-c) (test) | 16 | Feb 26, 2026 | ||
| Reading Comprehension | RACE Middle School | 16 | Feb 27, 2026 | ||
| Overall Language Performance | Aggregate All Benchmarks | 16 | Feb 26, 2026 | ||
| Long-context memory management | MemoryAgentBench | 16 | Jun 25, 2026 |