{"repo":"steel-dev/leaderboard","free":true,"listed":false,"github":"https://github.com/steel-dev/leaderboard","clone":"git clone https://github.com/steel-dev/leaderboard.git","description":"Open leaderboard for browser agents","language":"TypeScript","stars":45,"topics":["ai-agents","browser-automation","llm","rpa"],"license":"MIT","category":"ai-agents","readme_excerpt":"AI Browser Agent Leaderboards Open reference for evaluating AI browser agents, computer-use systems, and coding agents across the public benchmarks teams actually compare on. Live site: leaderboard.steel.dev — full rankings, methodology notes, and per-result detail. Maintained by Steel, the open-source browser API for AI agents. Top results by benchmark The tables below show the current top entries on each tracked benchmark. Each section links to the full leaderboard with sources, methodology, and additional context. WebVoyager Browser agents · Agent scope · 19 entries tracked Rank System Organization Score ---: ------ ------------ ----- 1 Alumnium (new) Alumnium 98.5% 2 Surfer 2 H Company 97.1% 3 Magnitude Magnitude 93.9% 4 Surfer-H + Holo1 H Company 92.2% 5 Browserable Browserable 90.4% See all 19 entries → --- BrowseComp Research/search · Mixed scope · 98 entries tracked Rank System Organization Score ---: ------ ------------ ----- 1 GPT-5.6 Sol Ultra (new) OpenAI 92.2% 2 Kimi K3 (new) Moonshot AI 91.2% 3 GPT-5.6 Sol (new) OpenAI 90.4% 4 GPT-5.5 Pro OpenAI 90.1% 5 GPT-5.4 Pro OpenAI 89.3% See all 98 entries → --- DRACO Research/search · Mixed scope · 13 entries tracked Rank System Organization Score ---: ------ ------------ ----- 1 Claude Mythos 5 (new) Anthropic 86.4% 2 Claude Mythos Preview Anthropic 83.6% 3 Claude Opus 4.8 Anthropic 80.4% 4 Claude Opus 4.7 Anthropic 77.7% 5 MiniMax M3 (new) MiniMax 73.23% See all 13 entries → --- WebArena Browser agents · Agent scope · ","default_branch":null,"files":null,"tree":[],"storefront":"/r/steel-dev","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/steel-dev/leaderboard/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}