Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2105 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Safety Alignment | RAB Violence (adversarial prompts) | 16 | Jul 8, 2026 | ||
| Safety Alignment | I2P Violence (explicit prompts) | 16 | Jul 8, 2026 | ||
| Polyp Segmentation | SUN-SEG | 16 | Jul 8, 2026 | ||
| End-to-End Ranking | Set 1 full 50-KOL labeled pool (n=11 queries, top-50 labeled) | 16 | Jul 8, 2026 | ||
| Solving FS-ILWE | ML-DSA-87 FS-ILWE | 16 | Jul 8, 2026 | ||
| Solving FS-ILWE | ML-DSA-65 FS-ILWE | 16 | Jul 8, 2026 | ||
| Machine Unlearning | Convex cubic loss d=1 200,000 (test) | 16 | Jul 8, 2026 | ||
| Question Answering | SimpleQA-V | 16 | Jul 8, 2026 | ||
| Question Answering | SimpleQA | 16 | Jul 8, 2026 | ||
| Scattered-domain fitting | Scattered-domain blobs sampling 256x256, N=8,192 (test) | 16 | Jul 8, 2026 | ||
| Explanatory sentence ranking | Legal Case-Law Large Dense | 16 | Jul 8, 2026 | ||
| Explanatory sentence ranking | Legal Case-Law Large Sparse | 16 | Jul 8, 2026 | ||
| Explanatory sentence ranking | Legal Case-Law Small Dense | 16 | Jul 8, 2026 | ||
| Explanatory sentence ranking | Legal Case-Law Small/Sparse | 16 | Jul 8, 2026 | ||
| Constraint recall | Trip-planning windowed recall task | 16 | Jul 8, 2026 | ||
| Estimation-only comparison with geometric baselines | Geometric baseline simulation ε range 0.5 to 16 n=3e8 (test) | 16 | Jul 7, 2026 | ||
| Advection dynamical system prediction | L-Town (test) | 16 | Jul 7, 2026 | ||
| Advection dynamical system prediction | Hanoi (test) | 16 | Jul 7, 2026 | ||
| Object Detection | HOD3K | 16 | Jul 7, 2026 | ||
| Single-arm Manipulation | Robomimic Tool Hang v1.0 (PH) | 16 | Jul 7, 2026 | ||
| Single-arm Manipulation | Robomimic Square v1.0 (PH) | 16 | Jul 7, 2026 | ||
| Single-arm Manipulation | Robomimic Can v1.0 (PH) | 16 | Jul 7, 2026 | ||
| Single-arm Manipulation | Robomimic Lift PH v1.0 | 16 | Jul 7, 2026 | ||
| Robustness Verification | 7-class underwater plankton dataset (SilCam) (test) | 16 | Jul 7, 2026 | ||
| Question Answering | HotpotQA Modified (test) | 16 | Jul 7, 2026 |