Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1134 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Efficiency Average | Consolidated Benchmarks All | 25 | Feb 26, 2026 | ||
| Memory | LoCoMo | 25 | Feb 26, 2026 | ||
| Agentic Benchmarks | GAIA | 25 | Feb 26, 2026 | ||
| Math Reasoning (coding tools) | BeyondBench Easy | 25 | Feb 26, 2026 | ||
| Retrieval | CommonsenseQA | 25 | Feb 26, 2026 | ||
| Retrieval | ARC Challenge | 25 | Feb 26, 2026 | ||
| Math Reasoning | BeyondBench Hard | 25 | Feb 26, 2026 | ||
| Math Reasoning | BeyondBench Easy | 25 | Feb 26, 2026 | ||
| Zero-shot Language Understanding | Evaluation Suite Zero-shot (LMB, HellA, PIQA, ARC-E, ARC-C, WINO, Open, MMLU) | 25 | Feb 26, 2026 | ||
| Biomedical reasoning | BioASQ out-of-domain | 25 | Feb 26, 2026 | ||
| Commonsense reasoning | PIQA (out-of-domain) | 25 | Feb 26, 2026 | ||
| Function-level Code Localization | SWE-bench Live Lite | 25 | Feb 26, 2026 | ||
| File-level Code Localization | SWE-bench Live Lite | 25 | Feb 26, 2026 | ||
| Function-level Code Localization | SWE-bench Verified (Lite) | 25 | Feb 26, 2026 | ||
| File-level Code Localization | SWE-bench Verified Lite | 25 | Feb 26, 2026 | ||
| Long-context understanding | InfiniteBench | 25 | Apr 21, 2026 | ||
| Machine Translation | WMT ZH-EN 24 | 25 | Apr 28, 2026 | ||
| Multi-Hop Question Answering | Bamboogle | 25 | Feb 26, 2026 | ||
| Retrieval | BRIDGE (test) | 25 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC23 | 25 | Feb 26, 2026 | ||
| Reasoning | CogniLoad Outcome suite 1.0 (m=10 m=100) | 25 | Feb 26, 2026 | ||
| General Knowledge | MMLU | 25 | Feb 26, 2026 | ||
| Inference Latency | JailbreakV | 25 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 25 | Feb 26, 2026 | ||
| Knowledge | CMMLU | 25 | May 26, 2026 |