# Science benchmarks AI Benchmark Index catalogs 24 science with source-linked metadata. 24 benchmarks. Also on the [web page](https://aibenchmarkindex.com/category/science). ## Benchmarks 1. [GEO-Bench](https://aibenchmarkindex.com/global/online/geo-bench.md), Science, Online: Compares pretrained models on a standardized suite of geospatial Earth-monitoring classification and segmentation datasets. 2. [GPQA](https://aibenchmarkindex.com/global/online/gpqa.md), Science, Online: Tests expert-level reasoning on graduate biology, physics, and chemistry questions designed to resist web search. 3. [LIBERO](https://aibenchmarkindex.com/global/online/libero.md), Science, Online: Measures knowledge transfer in lifelong robot learning across manipulation task suites with controlled distribution shifts. 4. [ManiSkill](https://aibenchmarkindex.com/global/online/maniskill.md), Science, Online: Measures generalizable robotic manipulation policies in scalable simulated environments. 5. [Matbench](https://aibenchmarkindex.com/global/online/matbench.md), Science, Online: Evaluates machine-learning models on 13 curated materials-property prediction tasks. 6. [Matbench Discovery](https://aibenchmarkindex.com/global/online/matbench-discovery.md), Science, Online: Compares the accuracy, robustness, and computational cost of models used for atomistic and materials-discovery tasks. 7. [MedMCQA](https://aibenchmarkindex.com/global/online/medmcqa.md), Science, Online: Evaluates medical multiple-choice reasoning on questions drawn from Indian medical entrance examinations. 8. [MedQA](https://aibenchmarkindex.com/global/online/medqa.md), Science, Online: Evaluates medical knowledge and reasoning with multiple-choice questions from professional medical licensing exams. 9. [Meta-World](https://aibenchmarkindex.com/global/online/meta-world.md), Science, Online: Measures multi-task and meta-reinforcement learning across robotic manipulation tasks and goal variations. 10. [MMLU Medical Subjects](https://aibenchmarkindex.com/global/online/mmlu-medical-subjects.md), Science, Online: Evaluates factual knowledge and problem solving across the medical and biomedical subject sets in MMLU. 11. [Mol-Instructions](https://aibenchmarkindex.com/global/online/mol-instructions.md), Science, Online: Evaluates instruction-following across molecule description, property prediction, reaction, and biomolecular tasks. 12. [OlympiadBench](https://aibenchmarkindex.com/global/online/olympiadbench.md), Science, Online: Tests bilingual, multimodal problem solving on olympiad-level mathematics and physics questions. 13. [Procgen Benchmark](https://aibenchmarkindex.com/global/online/procgen-benchmark.md), Science, Online: Measures sample efficiency and generalization in reinforcement learning across procedurally generated game environments. 14. [RLBench](https://aibenchmarkindex.com/global/online/rlbench.md), Science, Online: Measures robot learning across vision-guided manipulation tasks in a simulated environment. 15. [robomimic](https://aibenchmarkindex.com/global/online/robomimic.md), Science, Online: Measures robot policies learned from offline human demonstrations across standardized datasets and tasks. 16. [robosuite](https://aibenchmarkindex.com/global/online/robosuite.md), Science, Online: Provides standardized simulated robot manipulation environments for evaluating learning methods. 17. [ScienceWorld](https://aibenchmarkindex.com/global/online/scienceworld.md), Science, Online: Measures text-based agents on tasks grounded in an elementary science curriculum. 18. [SciFact](https://aibenchmarkindex.com/global/online/scifact.md), Science, Online: Tests retrieval of scientific evidence and classification of research claims as supported or refuted. 19. [Vendi Score](https://aibenchmarkindex.com/global/online/vendi-score.md), Science, Online: Measures diversity in a collection from pairwise similarities using the effective rank of a similarity matrix. 20. [AI2 Reasoning Challenge](https://aibenchmarkindex.com/global/online/ai2-reasoning-challenge.md), Science, Online: Tests grade-school science reasoning with natural multiple-choice questions split into easy and challenge sets. 21. [Benchmark Ranking Stability](https://aibenchmarkindex.com/global/online/benchmark-ranking-stability.md), Science, Online: Measures how much model rankings change across random seeds and prompt variants. 22. [MultiMedQA](https://aibenchmarkindex.com/global/online/multimedqa.md), Science, Online: Evaluates medical question answering across seven datasets spanning professional exams, research, and consumer health queries. 23. [PubMedQA](https://aibenchmarkindex.com/global/online/pubmedqa.md), Science, Online: Evaluates biomedical research question answering from PubMed abstracts, including an expert-annotated test set. 24. [SciBench](https://aibenchmarkindex.com/global/online/scibench.md), Science, Online: Evaluates college-level scientific reasoning, domain knowledge, and calculation on textbook problems. ## Science by city - [Online, Global](https://aibenchmarkindex.com/global/online/category/science.md): 24 benchmarks ## Related categories - [Multimodal](https://aibenchmarkindex.com/category/multimodal.md): 51 benchmarks - [Reasoning](https://aibenchmarkindex.com/category/reasoning.md): 50 benchmarks - [Agents](https://aibenchmarkindex.com/category/agents.md): 31 benchmarks - [Safety](https://aibenchmarkindex.com/category/safety.md): 25 benchmarks - [Coding](https://aibenchmarkindex.com/category/coding.md): 17 benchmarks - [Retrieval](https://aibenchmarkindex.com/category/retrieval.md): 17 benchmarks - [Memory](https://aibenchmarkindex.com/category/memory.md): 10 benchmarks - [Browser](https://aibenchmarkindex.com/category/browser.md): 7 benchmarks - [Voice](https://aibenchmarkindex.com/category/voice.md): 7 benchmarks - [Math](https://aibenchmarkindex.com/category/math.md): 6 benchmarks - [Other](https://aibenchmarkindex.com/category/other.md): 6 benchmarks - [Tools](https://aibenchmarkindex.com/category/tools.md): 6 benchmarks - [Commerce](https://aibenchmarkindex.com/category/commerce.md): 4 benchmarks - [Long-horizon](https://aibenchmarkindex.com/category/long-horizon.md): 3 benchmarks > **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.