Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1168 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Dialogue-Style Memory Reasoning | LoCoMo | 24 | Jun 11, 2026 | ||
| Single-task capability preservation | Qwen-Image | 24 | Jun 11, 2026 | ||
| Quadrotor motion planning | Quadrotor motion planning variational integrator | 24 | Jun 11, 2026 | ||
| Question Answering | Average (NQ, TabMWP, HotpotQA, TriviaQA, TriState) | 24 | Jun 11, 2026 | ||
| Question Answering | TriState | 24 | Jun 11, 2026 | ||
| Question Answering | Natural Questions (NQ) | 24 | Jun 11, 2026 | ||
| Question Answering | TriState-Bench | 24 | Jun 11, 2026 | ||
| Context-aware generation | TriState-Bench Agreement Sagr gold context, prior correct | 24 | Jun 11, 2026 | ||
| Context-aware generation | TriState-Bench Resistance corrupted context, prior correct (Sres) | 24 | Jun 11, 2026 | ||
| Context-aware generation | TriState-Bench Correction gold context, prior incorrect (Scor) | 24 | Jun 11, 2026 | ||
| PDE Surrogate Modeling | 2D Kuramoto-Sivashinsky and Gray-Scott | 24 | Jun 11, 2026 | ||
| Mathematical Reasoning and Safety Preservation | GSM8K | 24 | Jun 11, 2026 | ||
| Safety Alignment and Instruction Following | REDORCA | 24 | Jun 11, 2026 | ||
| Attack and collusion detection catch rate monitoring | BashArena (held-out 80% honest rollouts) | 24 | Jun 11, 2026 | ||
| Mathematical Reasoning | Average (MATH-OAI, Minerva Math, OlympiadBench, AIME24, AMC23) | 24 | Jun 9, 2026 | ||
| Mathematical Reasoning | AMC 23 | 24 | Jun 9, 2026 | ||
| Mathematical Reasoning | AIME 24 | 24 | Jun 9, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 24 | Jun 9, 2026 | ||
| Velocity Estimation | Simulated Events synthetic (test) | 24 | Jun 9, 2026 | ||
| Absolute Pose Estimation | Simulated Events synthetic (test) | 24 | Jun 9, 2026 | ||
| Anomaly Detection and Classification | MTD | 24 | Jun 9, 2026 | ||
| Anomaly Detection and Classification | MVTec FS | 24 | Jun 9, 2026 | ||
| Anomaly Localization | WFDD | 24 | Jun 9, 2026 | ||
| Diagnostic Endpoint Prediction | MMRF CoMMpass | 24 | Jun 9, 2026 | ||
| Concept Naming Evaluation | Lattice Concepts Trials 14 and 15 | 24 | Jun 9, 2026 |