Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2272 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Secure Inference | MNIST MiniONN | 16 | Feb 26, 2026 | ||
| Secure Inference (MiniONN) | MNIST (test) | 16 | Feb 26, 2026 | ||
| Reprompt forgery attack | COCO prompt (val) | 16 | Feb 26, 2026 | ||
| Reprompt forgery attack | SDP prompt (val) | 16 | Feb 26, 2026 | ||
| Rerouting Detection | MT-Bench (test) | 16 | Feb 26, 2026 | ||
| Rerouting Detection | GSM8k (test) | 16 | Feb 26, 2026 | ||
| Rerouting Detection | MMLU (test) | 16 | Feb 26, 2026 | ||
| Rerouting Detection | D (test) | 16 | Feb 26, 2026 | ||
| Directed Fuzzing | Go projects | 16 | Feb 26, 2026 | ||
| Steganographic secret extraction | TrojanStego T (test) | 16 | Feb 26, 2026 | ||
| Information Retrieval | NFCorpus | 16 | Feb 26, 2026 | ||
| Semantic Textual Similarity | STSB | 16 | Feb 26, 2026 | ||
| Privacy-utility tradeoff | FIQA | 16 | Feb 26, 2026 | ||
| Privacy-utility tradeoff | STS12 | 16 | Feb 26, 2026 | ||
| Text Generation | VPI Generation Tasks Llama3-8B Mistral-7B (test) | 16 | Feb 26, 2026 | ||
| Text Generation | AutoPoison Generation Llama3-8B Mistral-7B (test) | 16 | Feb 26, 2026 | ||
| Text Generation | DTBA Llama3-8B Mistral-7B (test) | 16 | Feb 26, 2026 | ||
| Jailbreak Attack | SafeBench | 16 | Feb 26, 2026 | ||
| Safety Evaluation | BeaverTails Text | 16 | Feb 26, 2026 | ||
| Agent Planning | AgentDojo | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 16 | Feb 26, 2026 | ||
| Sentiment Classification | Movie | 16 | Feb 26, 2026 | ||
| Free-form QA | FetaQA | 16 | Feb 26, 2026 |