Running 27 BrowserGym Leaderboard π 27 Tracks perf of LLMs, VLMs and agents on web navigation tasks
meta-llama/Llama-4-Scout-17B-16E-Instruct Image-Text-to-Text β’ 109B β’ Updated May 22, 2025 β’ 163k β’ β’ 1.34k
meta-llama/Llama-3.3-70B-Instruct Text Generation β’ 71B β’ Updated Dec 21, 2024 β’ 845k β’ β’ 3.01k
meta-llama/Llama-3.1-8B-Instruct Text Generation β’ 8B β’ Updated Sep 25, 2024 β’ 5.57M β’ β’ 6.81k
meta-llama/Meta-Llama-3-8B-Instruct Text Generation β’ 8B β’ Updated Jun 18, 2025 β’ 1.35M β’ β’ 4.92k
stable-diffusion-v1-5/stable-diffusion-v1-5 Text-to-Image β’ 0.9B β’ Updated Sep 7, 2024 β’ 1.56M β’ 1.27k