Saksham Arora · Chimera

Tag: Benchmarks

6 items with this tag.

  • Sep 23, 2026

    Grok 4.7 Doubled Its Terminal-Bench Score and Still Lost the Index

    • AI
    • Benchmarks
    • LLMs
    • Systems
  • Sep 14, 2026

    SWE-2 Hit 92.8% and 27.3% on the Same Leaderboard

    • AI-Systems
    • Coding-Agents
    • Benchmarks
    • Latency
  • Sep 10, 2026

    Magic Matched DeepSeek V4 Pro Base With 50x Fewer FLOPs

    • AI-Systems
    • Efficiency
    • Pretraining
    • Benchmarks
  • Sep 04, 2026

    OpenAI's Astra Just Scored 100% on the Benchmark That Finds Real Zero-Days

    • AI-Safety
    • Security
    • Systems
    • Benchmarks
  • Aug 22, 2026

    A Free Mystery Model Just Beat GPT-5.6 on Coding, and Nobody Audited the Number

    • LLM
    • Benchmarks
    • Systems
  • Jul 13, 2026

    GPT-5.6 Beats Claude by 13 Points on One Benchmark, Loses by 16 on Another

    • LLM
    • Benchmarks
    • Systems
    • Inference

  • GitHub
  • LinkedIn
  • X
  • Portfolio