Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 945 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Claim Verification | AVeriTeC Retrieved (H) (dev) | 28 | Apr 6, 2026 | ||
| Claim Verification | AVeriTeC Golden (dev) | 28 | Apr 6, 2026 | ||
| Reasoning | ARC-E | 28 | Jun 5, 2026 | ||
| Event-based Stereo Disparity Estimation | DSEC 18 (val) | 28 | Apr 3, 2026 | ||
| Face Manipulation Adversarial Attack | LFW | 28 | Apr 3, 2026 | ||
| Face Manipulation Adversarial Attack | FFHQ | 28 | Apr 3, 2026 | ||
| Face Manipulation Adversarial Attack | CelebA | 28 | Apr 3, 2026 | ||
| Star Discrepancy Evaluation | 4-dimensional point sets (D=4) | 28 | Apr 2, 2026 | ||
| Automated Exploit Generation | Penetration Testing Benchmark (test) | 28 | Apr 2, 2026 | ||
| Chatbot workload | Alpaca | 28 | Apr 2, 2026 | ||
| Chatbot workload | LMSYS-Chat-1M | 28 | Apr 2, 2026 | ||
| Medical Reasoning | MedCaseReasoning (test) | 28 | Apr 2, 2026 | ||
| Question Answering | HotpotQA (test) | 28 | Apr 2, 2026 | ||
| Contextual Privacy Leakage Evaluation | PrivaCI-Bench | 28 | Apr 2, 2026 | ||
| Contextual Privacy Leakage Evaluation | CONFAIDE Tier 3 | 28 | May 12, 2026 | ||
| Multilingual Question Answering | TyDiQA 1-shot macro-averaged | 28 | Apr 2, 2026 | ||
| Hallucination Evaluation | CHAIR MSCOCO 2014 | 28 | Apr 1, 2026 | ||
| Image embedding | LFW | 28 | Apr 1, 2026 | ||
| Weather Forecasting (V1000) | WeatherBench | 28 | Apr 1, 2026 | ||
| Weather Forecasting (U1000) | WeatherBench | 28 | Apr 1, 2026 | ||
| Weather Forecasting (V500) | WeatherBench | 28 | Apr 1, 2026 | ||
| Weather Forecasting (U500) | WeatherBench | 28 | Apr 1, 2026 | ||
| Weather Forecasting (Z850) | WeatherBench | 28 | Apr 1, 2026 | ||
| Weather Forecasting (T500) | WeatherBench | 28 | Apr 1, 2026 | ||
| Navier-Stokes Rollout Simulation | Canonical incompressible Navier-Stokes (test) | 28 | Apr 1, 2026 |