Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1695 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Global Optimization | CEC Functions F01-F30 D=50 2014 | 19 | Jun 5, 2026 | ||
| Numerical Optimization | CEC D=100 F01-F30 2014 | 19 | Jun 5, 2026 | ||
| Image Classification | ImageNet balanced original (test) | 19 | Jun 4, 2026 | ||
| Dynamic Link Prediction | tgbl-wiki (test) | 19 | Jun 11, 2026 | ||
| LLM Decoding Throughput | NOSA-8B 96K context length | 19 | Jun 4, 2026 | ||
| LLM Decoding Throughput | MiniCPM 8B 96K context length 4.1 | 19 | Jun 4, 2026 | ||
| Web Automation | WebArena | 19 | Jun 17, 2026 | ||
| Counseling Evaluation | PsychEval Resistant | 19 | Jun 4, 2026 | ||
| Counseling Evaluation | PsychEval Non-resistant | 19 | Jun 4, 2026 | ||
| Counseling Interaction Evaluation | PsychEval (Resistant) | 19 | Jun 4, 2026 | ||
| SQL fuzzing | SQL fuzzing benchmarks | 19 | Jun 4, 2026 | ||
| Time-bounded reachability computation | Erlang model | 19 | Jun 4, 2026 | ||
| Dual Face-Hair Retrieval | DFHR-Bench Bimodal Alignment | 19 | Jun 4, 2026 | ||
| Force and Energy Prediction | MD22 Ac-Ala3-NHMe + AT-AT | 19 | Jun 4, 2026 | ||
| Mathematical Reasoning | HMMT25 | 19 | Jun 30, 2026 | ||
| Natural Language Camera Agent | SCOPE | 19 | Jun 4, 2026 | ||
| Temporal video understanding | MotionBench | 19 | Jun 2, 2026 | ||
| Traveling Salesman Problem | DIMACS challenge E series 8th | 19 | Jun 2, 2026 | ||
| Regime Detection | Synthetic Time Series SVAR (Exp. Fam.) | 19 | Jun 2, 2026 | ||
| Mathematical reasoning | GSM8K | 19 | Jun 9, 2026 | ||
| Selective Prediction | NCQA (test) | 19 | Jun 2, 2026 | ||
| Tumor Segmentation | LiTS (test) | 19 | Jun 2, 2026 | ||
| UGC Quality Assessment | CASTER-Bench 1.0 (test) | 19 | Jun 2, 2026 | ||
| Task Incremental Learning (TIL) | Cora+WikiCS+Photo 10-shot (test) | 19 | Jun 2, 2026 | ||
| Domain Incremental Learning (DIL) | Cora+Citeseer+WikiCS 10-shot (test) | 19 | Jun 2, 2026 |