Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1635 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Planning-style reasoning | ACP prog-gen | 20 | Feb 26, 2026 | ||
| Text-Centric Vision-Language Understanding | OCR Bench | 20 | Feb 27, 2026 | ||
| Logical Reasoning | Deduction (test) | 20 | Feb 26, 2026 | ||
| Reasoning | General-domain reasoning benchmarks MATH, SuperGPQA, BBEH, MMLU-Pro | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | Math-domain reasoning benchmarks (MATH-500, Olympiad, Minerva, GSM8K, AMC, AIME24) (test) | 20 | Feb 26, 2026 | ||
| Reasoning | Big-bench Hard (BBH) | 20 | Feb 26, 2026 | ||
| Visual Instruction Following | FronTalk Single-Turn 1.0 (test) | 20 | Feb 26, 2026 | ||
| Throughput Measurement | LLaMA-2 13B | 20 | Feb 26, 2026 | ||
| Temporal Reasoning | TempReason-L3 in-domain (test) | 20 | Feb 26, 2026 | ||
| Temporal Reasoning | TempReason-L2 in-domain (test) | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | HMMT25 | 20 | Feb 26, 2026 | ||
| General Large Language Model Evaluation | Core Capabilities Aggregate | 20 | Feb 26, 2026 | ||
| Code Translation | Code Translation dataset | 20 | Feb 26, 2026 | ||
| Code Generation | MBPP | 20 | Feb 26, 2026 | ||
| Chain-of-Thought Reasoning | CoT-Collection | 20 | Feb 26, 2026 | ||
| Question Answering | OpenBookQA | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | OpenR1 Math 220k | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K | 20 | Feb 26, 2026 | ||
| Conversational Ability | Alpaca (test) | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH (test) | 20 | Feb 26, 2026 | ||
| Conversational Ability | Vicuna Eval (test) | 20 | Feb 26, 2026 | ||
| Information-Seeking | BrowseComp standard (full) | 20 | Feb 26, 2026 | ||
| Audio Understanding | MMAR (test) | 20 | Feb 26, 2026 | ||
| Mathematics | AIME 25 | 20 | May 28, 2026 | ||
| Mathematics | AIME 24 | 20 | May 28, 2026 |