Benchmark Almanac

Qualcomm AI Research

We track 4 benchmarks that Qualcomm AI Research made or helped make.

0 in use 3 with public code 3 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
QIVD Models answer spoken questions about short phone videos in real time, as in a face to face talk. Each item has a short answer and a timestamp. Video understanding Mar 2025 69.6% Fading
Ego-MC-Bench Models watch a cook follow spoken instructions and tell them when to correct a mistake. The evaluator checks intervention timing and recipe step completion. Video understanding Jun 2026 0.23 Not in cards
Qualcomm Interactive Cooking Models watch a cook follow a recipe. They give timed instructions, recognize completed steps, and warn about mistakes. The benchmark scores completion accuracy and mistake detection. Video understanding Nov 2025 23.1% Not in cards
QEVD-FIT-COACH Models watch a workout and decide when to give feedback. The benchmark scores feedback timing and the content of the coaching advice. Video understanding Jul 2024 Not in cards