<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
	<url>
		<loc>https://evals.study/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/in-brief/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmarks/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/science/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/tools/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/market/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/rules/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/asia/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/beyond-text/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/practice/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/opportunities/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/directory/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/market-map/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/methodology/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/glossary/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/mmlu/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/mmlu-pro/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/gpqa-diamond/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/hle/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/hle-diamond/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/arc-agi-1/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/arc-agi-2/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/arc-agi-3/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/simpleqa-verified/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/browsecomp/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/critpt/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/cmt-benchmark/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/lech-mazur-writing/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/textquests/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/frontiermath-tiers-1-3/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/frontiermath-tier-4/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/frontiermath-erdos/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/math-level-5/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/otis-mock-aime/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/matharena/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/imo-2026/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/swe-bench-verified/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/swe-bench-pro/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/deepswe/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/terminal-bench-4/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/frontiercode/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/cursorbench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/gso/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/osworld-verified/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/osworld-2/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/osworld-2-1/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/agents-last-exam/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/gdpval-aa/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/remote-labor-index/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/vending-bench-2/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/tau2-bench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/tau3-banking/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/bfcl-v4/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/metr-time-horizon/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/legalbench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/harvey-lab/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/hlab-vals/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/eu-agent-bench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/aithos-lara/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/vals-finance-agent/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/insclaimbench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/medqa/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/healthbench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/healthbench-professional/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/euroeval/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/mmlu-prox/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/harmbench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/xstest/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/agentharm/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/agentdojo/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/mask/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/wmdp/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/vct/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/cybench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/exploitbench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/screenspot-pro/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/mmmu/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/mmmu-pro/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/docvqa/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/hallusionbench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/video-mme/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/geneval/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/geneval-2/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/deepfake-eval-2024/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/big-bench-audio/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/tau-voice/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/open-asr-leaderboard/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/libero/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/behavior-1k/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/navsim/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/nuscenes-open-loop/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/lmarena/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/c-eval/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/cmmlu/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/superclue/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/foresightsafety-bench/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
	<url>
		<loc>https://evals.study/benchmark-checker/indicsafe/</loc>
		<lastmod>2026-11-05</lastmod>
	</url>
</urlset>
