datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
grocery-bench
Grocery Bench
30-turn multi-turn speech-to-speech benchmark for evaluating voice AI models as a grocery ordering assistant.
Part of Audio Arena, a suite of 6 benchmarks spanning 221 turns across different domains. Built by Arcada Labs.
Leaderboard | GitHub | All Benchmarks
Dataset Description
The model acts as a grocery ordering assistant helping a customer build, modify, and finalize an order. The conversation is designed around 15 difficulty enhancements that… See the full description on the dataset page: https://huggingface.co/datasets/arcada-labs/grocery-bench.product-bench
Product Bench
31-turn multi-turn speech-to-speech benchmark for evaluating voice AI models as a laptop comparison shopping assistant.
Part of Audio Arena, a suite of 6 benchmarks spanning 221 turns across different domains. Built by Arcada Labs.
Leaderboard | GitHub | All Benchmarks
Dataset Description
The model acts as a laptop comparison shopping assistant helping a customer evaluate, compare, and order laptops. The conversation features multi-intent turns… See the full description on the dataset page: https://huggingface.co/datasets/arcada-labs/product-bench.appointment-bench
Appointment Bench
25-turn multi-turn speech-to-speech benchmark for evaluating voice AI models as a dental office receptionist handling appointment scheduling.
Part of Audio Arena, a suite of 6 benchmarks spanning 221 turns across different domains. Built by Arcada Labs.
Leaderboard | GitHub | All Benchmarks
Dataset Description
The model acts as a dental office receptionist scheduling appointments for two patients with confusable names (Daniel and Danielle Nolan)… See the full description on the dataset page: https://huggingface.co/datasets/arcada-labs/appointment-bench.conversation-bench
Conversation Bench
75-turn multi-turn speech-to-speech benchmark for evaluating voice AI models as a conference assistant for the AI Engineer World's Fair.
Part of Audio Arena, a suite of 6 benchmarks spanning 221 turns across different domains. Built by Arcada Labs.
Leaderboard | GitHub | All Benchmarks
Dataset Description
The model acts as a conference assistant for the AI Engineer World's Fair, handling session registration, schedule queries, speaker lookups, and… See the full description on the dataset page: https://huggingface.co/datasets/arcada-labs/conversation-bench.assistant-bench
Assistant Bench
31-turn multi-turn speech-to-speech benchmark for evaluating voice AI models as a personal assistant handling flights, email, calendar, and reminders.
Part of Audio Arena, a suite of 6 benchmarks spanning 221 turns across different domains. Built by Arcada Labs.
Leaderboard | GitHub | All Benchmarks
Dataset Description
The model acts as a personal assistant managing flight bookings, email composition, calendar events, and reminders. Turns include dual… See the full description on the dataset page: https://huggingface.co/datasets/arcada-labs/assistant-bench.event-bench
Event Bench
29-turn multi-turn speech-to-speech benchmark for evaluating voice AI models as an event planning assistant.
Part of Audio Arena, a suite of 6 benchmarks spanning 221 turns across different domains. Built by Arcada Labs.
Leaderboard | GitHub | All Benchmarks
Dataset Description
The model acts as an event planning assistant managing venue bookings, catering, and guest logistics. The conversation features cascading changes — a venue switch triggers catering… See the full description on the dataset page: https://huggingface.co/datasets/arcada-labs/event-bench.