Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2145 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Test-Time Scaling Selection | RouterBench Quality-Priority | 16 | Jun 1, 2026 | ||
| Test-Time Scaling Selection | RouterBench Cost-Sensitive | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | AgentGym Unweighted Average (test) | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | Wordle (test) | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | WebShop (test) | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | TextCraft (test) | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | SciWorld (test) | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | Maze (test) | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | BabyAI (test) | 16 | Jun 1, 2026 | ||
| One-step next-observation prediction | AlfWorld (test) | 16 | Jun 1, 2026 | ||
| Forecasting | FutureX | 16 | Jun 1, 2026 | ||
| Forecasting | Prophet Arena | 16 | Jun 1, 2026 | ||
| Safety Evaluation | WildTeaming | 16 | Jun 1, 2026 | ||
| Temporal Sentence Grounding | Charades-STA (test) | 16 | Jun 1, 2026 | ||
| Web-based Shopping Simulation | WebShop (test) | 16 | Jun 1, 2026 | ||
| Embodied Task Completion | ALFWorld (test) | 16 | Jun 1, 2026 | ||
| Question Answering | OBQA | 16 | Jun 15, 2026 | ||
| Safety-Utility Trade-off | IFEval and AdvBench | 16 | Jun 1, 2026 | ||
| General Reasoning | ARC Challenge | 16 | Jun 1, 2026 | ||
| Instruction Following | IFEval | 16 | Jun 1, 2026 | ||
| Text Classification | MARC English | 16 | Jun 1, 2026 | ||
| Text Classification | MARC French | 16 | Jun 1, 2026 | ||
| Ad-Injected Response Generation | LM-Market | 16 | Jun 1, 2026 | ||
| Ad-Injected Response Generation | MT-Human | 16 | Jun 1, 2026 | ||
| Dynamic Manipulation | DOMINO 35 suites (full) | 16 | May 29, 2026 |