Additionally, the Workflow evals results assessing four business workflows are as follows:<\/p>\n
\n
\u2192 Scroll horizontally to see all columns<\/p>\n
\n\n\n| Workflow<\/th>\n | Metric<\/th>\n | Clef<\/th>\n | Clef-flash<\/th>\n | Jev<\/th>\n<\/tr>\n<\/thead>\n |
\n\n| Invoice processing<\/td>\n | Exact actions<\/td>\n | 64.7<\/strong><\/td>\n| 57.1<\/td>\n | 61.8<\/td>\n<\/tr>\n | \n| Invoice processing<\/td>\n | Primary action<\/td>\n | 86.2<\/strong><\/td>\n| 73.3<\/td>\n | 83.1<\/td>\n<\/tr>\n | \n| Customer service<\/td>\n | Exact actions<\/td>\n | 76.3<\/td>\n | 77.0<\/strong><\/td>\n| 76.0<\/td>\n<\/tr>\n | \n| Security incidents<\/td>\n | Exact actions<\/td>\n | 62.9<\/strong><\/td>\n| 61.7<\/td>\n | 61.7<\/td>\n<\/tr>\n | \n| Agent trace observability<\/td>\n | Primary action<\/td>\n | 68.5<\/td>\n | 69.8<\/td>\n | 71.6<\/strong><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n According to measurements by the publishers, the Clef model outperforms other models such as Jev on metrics measuring tool use and function selection accuracy, including BFCL, ToolRet, and API-Bank, while holding a distinct advantage in latency (such as median latency). On the other hand, Jev scores higher on certain reasoning and commonsense reasoning metrics such as ANLI, BRIGHT, MMLU-Pro, and BBH, indicating that performance varies by task rather than being universally superior. Meanwhile, Clef-flash successfully reduces latency significantly while maintaining accuracy.<\/p>\n Strengths and Use Cases<\/h2>\nClef is a decision model that accepts text, JSON, images, and video as inputs and returns structured answers with probabilities for specified questions or schemas in a single forward pass, without requiring free-form text generation or output parsing. It is well-suited for use cases such as web domain classification, invoice processing, customer support routing, security incident triage, and agent decision processing. Furthermore, equipped with a vision encoder, it can also classify visual content contained in images and videos. The base model, Qwen3.8-27B, inherently boasts strengths in coding, professional tasks, research, and general long-context agent tasks.<\/p>\n How It Differs from Similar Models<\/h2>\nModels based on Qwen3.8-27B include OrcaSAQ-2-27B<\/code><\/a>, which focuses on lightweight deployment via quantization, and Hemmingway-1<\/code><\/a>, which specializes in everyday text writing. While these are primarily aimed at standard text generation and composition, Clef specializes in classification and decision-making, significantly differing in that it returns fast, consistent typed outputs with probabilities without performing extraneous text generation.<\/p>\n<\/p>\n Hardware Requirements<\/h2>\nEstimated requirements (calculated by Local Model Watch)<\/strong> \u2014 27.4B parameters<\/p>\n | | | | |