Bo-Eval v1 Bo-Eval v1 is the premier open-source benchmark for Tibetan AI. It rigorously evaluates LLM reasoning and STT accuracy across diverse dialects. MonlamAI/Bo-bench-v1.0.0 Viewer • Updated Apr 16 • 6.12k • 57 MonlamAI/Bo-voice-v1.0.0 Viewer • Updated Apr 16 • 8.37k • 64
Bo-Eval v1 Bo-Eval v1 is the premier open-source benchmark for Tibetan AI. It rigorously evaluates LLM reasoning and STT accuracy across diverse dialects. MonlamAI/Bo-bench-v1.0.0 Viewer • Updated Apr 16 • 6.12k • 57 MonlamAI/Bo-voice-v1.0.0 Viewer • Updated Apr 16 • 8.37k • 64
