Running Agents 111 Judge Arena π» 111 View and compare openβsource AI model rankings with ELO scores
AtlaAI/Selene-1-Mini-Llama-3.1-8B Text Generation β’ 8B β’ Updated Jul 25, 2025 β’ 940 β’ β’ 104
Selene 1 Collection Our most powerful evaluation model, Selene 1 beats frontier models from leading labs. Learn more here: https://www.atla-ai.com/post/selene-1 β’ 2 items β’ Updated Jul 24, 2025
AtlaAI/Selene-1-Mini-Llama-3.1-8B-GPTQ-W8A8 Text Generation β’ 8B β’ Updated Jul 25, 2025 β’ 5 β’ 2
AtlaAI/Selene-1-Mini-Llama-3.1-8B-GPTQ-W4A16 Text Generation β’ 2B β’ Updated Jul 25, 2025 β’ 4 β’ 1
AtlaAI/Selene-1-Llama-3.3-70B-GPTQ-W8A8 Text Generation β’ 71B β’ Updated Jul 25, 2025 β’ 32 β’ 2