Daniel Ivanov
RURSS

Notes tagged

#benchmark

5 posts

  • 2026-08-293 min read

    GPT-5.6 Luna costs 10x less than Claude Sonnet 5 — and scored exactly the same

    Ran my own benchmark against six closed models and four local ones — and found two cases where the top models silently refused completely benign tasks.

  • 2026-07-204 min read

    The coach assistant: 32 sources, 70 questions, 77.4%

    The corpus grew from 9 to 32 sources. The re-run scored 77.4% on 70 questions, with 10/10 grounding in the new module.

  • 2026-07-084 min read

    60 coach questions: why niche AI needs its own benchmark

    First basketball slice of LII Sport Bench: 60 questions, 9 public RFB Academy sources, and the first numbers for the RAG assistant.

  • 2026-07-075 min read

    Russian open models on my own Blackwell — and where NVFP4 breaks

    An open RU-model ladder on an RTX PRO 6000: the dense 27B takes the top, a 12B lands half a step behind at half the size, and NVFP4 on Blackwell came up for only one of three.

  • 2026-07-072 min read

    Fixed NVFP4 on Blackwell — it was missing CUDA 12.9

    Two Blackwell bugs turned out to be one CUDA-toolkit gap, not a vLLM bug. Both models run NVFP4 now; memory ran 4-5GB heavier than the morning estimate.

← Back to all notes
Daniel Ivanov · csylabsПолитика обработки ПДн© 2026