AI VIDEOS
Menu

Model Evaluation Videos

Videos that compare AI models through benchmarks, hands-on tests, cost analysis, and practical task performance.

Search the index

Find videos

Showing 261–280 of 355 videos

Clear filters
  1. The words Gemini Wins at Chess beside a flat blue knight above toppled pieces
    Gemini Wins the AI Chess Tournament
    No Hype AI18m 32s1 VIEW
  2. Will Brown in glasses and a blue shirt rests a hand on his chin beside the blue and white headline RL beyond easy rewards on black.
    Reinforcement Learning without Verifiable Rewards - Will Brown, Prime Intellect
    AI Engineer19m 27s
  3. Portrait of Bijan Bowen beside the words DeepSeek Flash Punches Up
    DeepSeek V4 Flash Is Insane: The Best Small Model Yet!
    Bijan Bowen36m 57s
  4. Brent A. Anders beside the two-color headline AI Is Not Conscious Yet
    Why AI Is Not Conscious Yet
    Sovorel27m 57s
  5. A flat attention-blue AI chip and a white terminal cursor sit beside the headline Agentic Coding Comeback on a pure black background.
    DeepSeek V4 Flash Shows Strong Agentic Coding Gains
    AICodeKing11m 35s1 VIEW
  6. Matthew Berman in white, Andrej Karpathy in blue and Sam Altman in pink above the blue and white headline GPT-5.6 SOL - EFFICIENCY LOOPS on black.
    GPT-5.6 just made itself better...
    Matthew Berman14m 45s
  7. Three flat attention-blue AI chips sit beside the headline 3 Gemini Models One Big Shift on a pure black background.
    Three New Gemini Models Target Efficient Agent Work
    TheAIGRID8m 50s
  8. Tim Simmons against a black background beside the blue-and-white headline “VIDEO AI REALITY CHECK”.
    MiniMax Just Dropped a Open Source "Seedance Killer"
    Theoretically Media19m 36s1 VIEW
  9. Portrait of Bijan Bowen beside the words Two Agents Build the Game
    GPT-5.6 and Fable 5 Build a Full-Stack Game
    Bijan Bowen28m 28s1 VIEW
  10. Nick Saraev, Jack Roberts and Ilya Sutskever beneath the blue and white headline AI DATA AND COMPUTE on black.
    Nick Saraev and Jack Roberts on AI Data and Compute
    Stacked Podcast35m 41s
  11. Portrait of Bijan Bowen beside the words Small Model Big Coding
    Ling 3.0 Flash First Test: A Surprisingly Good Coding Model!
    Bijan Bowen26m 50s3 VIEWS
  12. Blue-and-white headline “OPUS BUILDS WORLDS” beside three large grey stepped blocks and a blue arched doorway on black.
    Claude Opus 5 Games, Simulations and Interactive Demos
    TheAIGRID17m 59s
  13. Nathaniel Whittemore in a blue top beside the blue-and-white headline “OPUS IN YOUR STACK” on black.
    Where Claude Opus 5 Fits in a Practical Model Rotation
    The AI Daily Brief28m 45s
  14. Riley Brown in a blue top beside the blue-and-white headline “CLAUDE IN EXCEL” on black.
    Riley Brown Tests Claude Opus 5 in Excel
    Riley Brown21m 3s2 VIEWS
  15. Alejandro Vidal beside the words Benchmarks Miss Difficulty
    Why Psychometrics Can Improve LLM Evaluation
    AI Engineer23m 35s
  16. Susheem Koul and Tisha Chawla beside the words Replay Agent Failures
    How to Replay and Debug AI Agent Failures
    AI Engineer14m 11s
  17. Portrait of Nate B. Jones beside the words Test the Task Not the Flag
    US AI Dominance Is Over: Here's Why
    Nate B Jones24m 1s
  18. The blue and white headline 'CREATIVE AGENTS COST' surrounded by flat workflow icons for documents, a gear, a robot, an idea, chat and video on black.
    AI Search Tests Claude Opus 5 on Creative Tasks and Cost
    AI Search32m 44s
  19. Theo Browne beside the words Open Model Closes the Gap
    Why Kimi K3 Is Pressuring Frontier AI Labs
    Theo36m
  20. Blue and white lines merge into an arrow pointing to a checkmark beneath the blue-and-white headline “OPEN MODELS REAL LIMITS” on black.
    Claude Opus 5, GPT 6 hack, Flux 3, new Gemini, quantum breakthrough, new Qwen: AI NEWS
    AI Search44m 24s