--- id: "/evaluation-benchmarks/science-domain-evals/" title: "science & domain evals: 45 curated resources" url: "https://skillissue.dev/evaluation-benchmarks/science-domain-evals/" --- # science & domain evals: 45 curated resources science & domain evals [Beginner](/evaluation-benchmarks/beginner/index.md) [Intermediate](/evaluation-benchmarks/intermediate/index.md) [Advanced](/evaluation-benchmarks/advanced/index.md) [Expert](/evaluation-benchmarks/expert/index.md) 45 resources ยท page 1 of 2 - ### [ARC-AGI leaderboard](/evaluation/benchmarks-and-leaderboards/arc-agi-leaderboard/index.md) by [ARC Prize Foundation](https://arcprize.org/) ARC Prize leaderboard: model scores on ARC-AGI abstraction benchmarks plotted against cost per task. entity leaderboard West en - ### [BEIR](/evaluation/benchmarks-and-leaderboards/beir/index.md) by [BEIR Cellar](https://github.com/beir-cellar) BEIR GitHub repo: heterogeneous information-retrieval benchmark of many datasets for zero-shot evaluation of retrievers. entity benchmark Germany / UK en - ### [CAMEO](/evaluation/benchmarks-and-leaderboards/cameo/index.md) by [CAMEO (SIB Swiss Institute of Bioinformatics)](https://www.cameo3d.org/) CAMEO platform: weekly automated, blind benchmarking of protein structure prediction servers against newly released structures. entity benchmark Switzerland / International en - ### [CASP Prediction Center](/evaluation/benchmarks-and-leaderboards/casp-protein-structure-prediction/index.md) by [Protein Structure Prediction Center (UC Davis)](https://predictioncenter.org/) CASP Prediction Center: blind community assessment of protein structure prediction methods. entity leaderboard West en - ### [CASP17](/evaluation/benchmarks-and-leaderboards/casp17/index.md) by [Protein Structure Prediction Center (UC Davis)](https://predictioncenter.org/) CASP17 site: the 2026 round of the Critical Assessment of protein Structure Prediction, with targets and assessment results. entity community US (UC Davis, NIH-funded) en - ### [DREAM Challenges](/evaluation/benchmarks-and-leaderboards/dream-challenges/index.md) by [Sage Bionetworks (DREAM Challenges)](https://sagebionetworks.org/) Sage Bionetworks page for DREAM Challenges: community biomedical challenges with held-out data and evaluation protocols. entity benchmark International en - ### [HealthBench Professional: Benchmark review (Epoch AI)](/evaluation/benchmarks-and-leaderboards/epoch-ai-healthbench-professional-review/index.md) by [Epoch AI](https://epoch.ai/) Epoch AI review of HealthBench Professional, auditing sampled tasks for errors and assessing the benchmark's reliability. entity benchmark US (non-profit) en - ### [FinanceBench](/evaluation/benchmarks-and-leaderboards/financebench/index.md) by [patronus-ai](https://github.com/patronus-ai) FinanceBench GitHub repo from Patronus AI: open-book financial question answering over public company filings. entity benchmark US (Patronus AI) en - ### [FinanceBench (Patronus AI)](/evaluation/benchmarks-and-leaderboards/financebench-patronus-ai/index.md) by [Patronus AI](https://www.patronus.ai/) Patronus AI announcement of FinanceBench, question answering over public financial filings to measure LLM failures. entity benchmark US en - ### [FrontierMath](/evaluation/benchmarks-and-leaderboards/frontiermath/index.md) by [Epoch AI](https://epoch.ai/) Epoch AI FrontierMath: benchmark of unpublished expert-level mathematics problems in tiers, with model results. entity leaderboard West en - ### [GPQA](/evaluation/benchmarks-and-leaderboards/gpqa/index.md) by [I. David Rein](https://idavidrein.com) GPQA GitHub repo: graduate-level, Google-proof science questions with baselines for evaluating expert reasoning. entity benchmark US en - ### [GSM8K](/evaluation/benchmarks-and-leaderboards/gsm8k/index.md) by [OpenAI](https://openai.com/) GSM8K GitHub repo from OpenAI: grade-school math word problems with solutions and evaluation code; archived. entity benchmark US en - ### [GuacaMol](/evaluation/benchmarks-and-leaderboards/guacamol/index.md) by [BenevolentAI](https://github.com/BenevolentAI) BenevolentAI GuacaMol GitHub repo: benchmarks for generative chemistry models. entity repo UK en - ### [LAB-Bench](/evaluation/benchmarks-and-leaderboards/lab-bench-github/index.md) by [FutureHouse](https://futurehouse.org) LAB-Bench GitHub repo from FutureHouse: practical biology-research tasks such as literature, sequence and protocol questions. entity benchmark US (FutureHouse) en - ### [LegalBench](/evaluation/benchmarks-and-leaderboards/legalbench/index.md) by [Hazy Research (Stanford University)](https://hazyresearch.stanford.edu/) LegalBench site from Stanford: collaboratively built benchmark of legal-reasoning tasks for evaluating LLMs on US law. entity benchmark US (Stanford) en - ### [LiveMedBench](/evaluation/benchmarks-and-leaderboards/livemedbench/index.md) by [alphaXiv](https://www.alphaxiv.org/) LiveMedBench paper page: a continuously refreshed medical LLM benchmark built from real clinical cases with automated rubric scoring. entity benchmark unstated en - ### [Matbench](/evaluation/benchmarks-and-leaderboards/matbench/index.md) by [Materials Project](https://www.materialsproject.org) Materials Project Matbench GitHub repo: benchmark tasks for materials property prediction. entity repo US / International en - ### [Matbench Discovery](/evaluation/benchmarks-and-leaderboards/matbench-discovery/index.md) by [Janosh Riebesell](https://janosh.dev) Matbench Discovery GitHub repo: evaluation framework for ML models in materials stability discovery. entity repo International en - ### [MATH](/evaluation/benchmarks-and-leaderboards/math/index.md) by [Dan Hendrycks](https://danhendrycks.com) MATH dataset GitHub repo: competition mathematics problems with step-by-step solutions for evaluating reasoning. entity benchmark US en - ### [MathArena](/evaluation/benchmarks-and-leaderboards/matharena/index.md) by [MathArena team (SRI Lab, ETH Zurich)](https://matharena.ai/) MathArena: evaluation of LLMs on newly released math competitions and arXiv-derived problems to avoid contamination. entity leaderboard Switzerland (ETH SRI) en - ### [MedBench](/evaluation/benchmarks-and-leaderboards/medbench/index.md) by [Shanghai AI Laboratory (OpenCompass)](https://opencompass.org.cn/) OpenCompass MedBench portal: Chinese medical benchmark platform for evaluating LLMs on clinical knowledge and tasks. entity benchmark China zh - ### [MedHELM](/evaluation/benchmarks-and-leaderboards/medhelm/index.md) by [Stanford CRFM](https://crfm.stanford.edu/) Stanford CRFM MedHELM: evaluation of language models on clinician-defined medical tasks beyond exam-style questions. entity benchmark US en - ### [MedHELM (Stanford CRFM)](/evaluation/benchmarks-and-leaderboards/medhelm-stanford-crfm/index.md) by [Stanford CRFM](https://crfm.stanford.edu/) Latest MedHELM results page from Stanford CRFM, scoring language models on a taxonomy of real clinical tasks. entity benchmark US (Stanford) en - ### [MedMNIST](/evaluation/benchmarks-and-leaderboards/medmnist/index.md) by [MedMNIST team (Shanghai Jiao Tong University)](https://medmnist.com/) MedMNIST site: standardised 2D and 3D biomedical image classification datasets for lightweight benchmarking. entity benchmark China / International en - ### [MERA Industrial](/evaluation/benchmarks-and-leaderboards/mera-industrial/index.md) by [AI Alliance Russia](https://a-ai.ru/) MERA Industrial: benchmark of foundation models on industry-specific Russian-language tasks. entity leaderboard Russia ru - ### [MOSES](/evaluation/benchmarks-and-leaderboards/moses/index.md) by [MOSES](https://github.com/molecularsets) MOSES GitHub repo: benchmarking platform with metrics and baselines for molecular generation models. entity repo Russia / International en - ### [Open Catalyst Project](/evaluation/benchmarks-and-leaderboards/open-catalyst-project/index.md) by [Meta FAIR Chemistry and Carnegie Mellon University (Open Catalyst Project)](https://opencatalystproject.org/) Open Catalyst Project site: atomistic datasets, models and challenges for AI-based catalyst discovery. entity benchmark US / International en - ### [Open Graph Benchmark](/evaluation/benchmarks-and-leaderboards/open-graph-benchmark/index.md) by [Open Graph Benchmark team (Stanford University)](https://ogb.stanford.edu/) Open Graph Benchmark site from Stanford: graph datasets, data loaders and evaluators for graph machine learning. entity benchmark US / International en - ### [frontier-evals](/evaluation/benchmarks-and-leaderboards/openai-frontier-evals-paperbench-etc/index.md) by [OpenAI](https://openai.com/) OpenAI frontier-evals GitHub repo: code for evaluations such as PaperBench and SWE-Lancer. entity leaderboard West en - ### [PhysioNet Challenges](/evaluation/benchmarks-and-leaderboards/physionet-challenges/index.md) by [PhysioNet (MIT Laboratory for Computational Physiology)](https://physionet.org/) PhysioNet Challenges page: annual open challenges on clinical physiological-signal analysis with scoring methods and data. entity benchmark US / International en - ### [ProteinGym](/evaluation/benchmarks-and-leaderboards/proteingym/index.md) by [Marks Lab (Harvard Medical School)](https://www.proteingym.org/) ProteinGym: benchmark and leaderboard for predicting the effects of protein mutations. entity leaderboard West en - ### [Robot learning leaderboard (RoboArena)](/evaluation/benchmarks-and-leaderboards/robot-learning-leaderboard-roboarena/index.md) by [RoboArena team (Pranav Atreya, Karl Pertsch et al.)](https://www.robot-learning.ml/) Robot-learning.ml leaderboard site for evaluating robot learning policies. entity leaderboard West [Next page](/evaluation-benchmarks/science-domain-evals/page/2/index.md) [Plain-text Markdown copy](/evaluation-benchmarks/science-domain-evals/index.md)