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 321–340 of 355 videos

Clear filters
  1. Portrait of Bijan Bowen beside the words One Bit Runs on a Phone
    Bonsai 27B Low-Bit Local Model Test
    Bijan Bowen33m 45s1 VIEW
  2. Portrait of Bijan Bowen beside the words Inkling's Open Model Falls Short
    Inkling Open Model First Test
    Bijan Bowen30m 48s
  3. Nate B. Jones gesturing beside the blue and white words Choose AI by Work Style
    Choose AI Models by Work Style, Not Benchmarks
    Nate B Jones13m 27s
  4. Theo Browne in a blue top against black beside the blue-and-white headline “Persistent, Not Perfect”.
    GPT-5.6 - The Review
    Theo36m1 VIEW
  5. Theo Jaffee in an off-white top and Matthew Berman in blue gesturing beside the blue-and-white headline FRONTIER VS WORKHORSE on black.
    Did This Save SpaceXAI? - Matthew Berman
    MTS23m 11s
  6. Blue-and-white headline GROK'S AGENT COMEBACK beside a simple flat branching upward arrow on a black background.
    Grok 4.5 Tested: Coding, Reasoning and Agent Limits
    AICodeKing12m 9s1 VIEW
  7. Blue GPT-5.6 and white MIXED RESULTS headline above a flat balance beam with blue and pale blocks on a black background.
    GPT-5.6 Tests: Agent Builds, Visual Failures and Benchmark Caveats
    AI Search25m 59s
  8. Bijan Bowen in a blue top at left beside the blue and white headline GREAT MODEL ROUGH EXPERIENCE on a black background.
    GPT-5.6: Strong Builds, Unfinished Hardware Work and Interface Friction
    Bijan Bowen44m 9s
  9. Kristian Fagerlie in a blue top at left beside the blue and white headline STRATEGY IS NOT PROOF on a black background.
    GPT-5.6 Strategy Research: A Cautious Prediction-Market Comparison
    All About AI15m 37s
  10. Alex Finn in a blue top on the left, resting one hand at his chin beside the blue and white headline PLAN, THEN EXECUTE against black.
    GPT-5.6 Execution, Fable Planning and a Remote Coding Workflow
    Alex Finn19m 40s
  11. Matthew Berman against black beside the blue-and-white headline "PROTOTYPE IS NOT PARITY".
    Matthew Berman on Long-Running Coding Agents and Model Routing
    Matthew Berman8m 55s
  12. Two flat document shapes and a blue check mark beside the white-and-blue headline "TEST THE REAL TASK" on black.
    The AI Grid on Grok Coding Claims and Benchmark Limits
    TheAIGRID18m 21s
  13. One flat blue wrench with an off-white open end on the right beside the blue and white headline AGENTS VS UI against black.
    GPT-5.6 in KingBench 3: Agentic Strengths and Front-End Gaps
    AICodeKing5m 48s
  14. Theo Browne in a blue top beside the blue-and-white headline “GROK NEEDS GUARDRAILS” against a black background.
    Grok 4.5: Practical Coding, Efficiency and Orchestration Limits
    Theo24m 44s
  15. Bijan Bowen beside the blue and white words Grok 4.5 Surprises
    Grok 4.5 Surprises in Real Coding Tests
    Bijan Bowen39m 51s
  16. Wes Roth in a blue top beside the blue-and-white headline “PLAN THEN DELEGATE” against a black background.
    Grok 4.5: Game Prototypes and Model Delegation
    Wes Roth35m 20s
  17. A flat white checkmark between two blue code brackets above the blue and white headline "TEST THE WHOLE HARNESS" on black.
    Fable 5 VS Opus 4.8 VS GLM 5.2: Can GLM 5.2 WIN?
    AICodeKing11m 28s
  18. Hanna Lichtenberg in light blue on the left and Aamir Shakir in dark blue on the right, beside the blue-and-white headline “Evidence-First Search” against black.
    Training Retrieval Agents for Evidence-First Search
    AI Engineer14m 28s1 VIEW
  19. David Ondrej beside the words Fine-Tune Giant Open Models
    How to Fine-Tune Giant Open Models
    David Ondrej29m 8s
  20. Blue and white text "CLAIMS NEED A TEST" beside a large blue checkmark over an off-white square on black.
    Tencent Hy3 tested on coding, reasoning and agent tasks
    AICodeKing7m 11s