← 최신 프로덕트

Benchmark

AI doesn't find bugs unless you tell it what's wrong. New benchmark from researchers at Meta, Stanford, Harvard, UW, including the researchers who've worked on SWE-bench, ProgramBench etc.

swesweep.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. New Benchmark from SWE-bench team is 0% solved

    programbench.com

    ProgramBench evaluates whether language models can rebuild programs from scratch.

    Hacker News24점

  2. ML-Dev-Bench

    github.com

    Benchmarking AI Agents on Real-World AI Workflows

    Hacker News6점

  3. A registry of agent benchmarks (including many OSS agent trajectories)

    explorer.invariantlabs.ai

    A better way of testing, inspecting, and analyzing AI Agent traces. - invariantlabs-ai/explorer

    Hacker News6점

  4. AI Browser Agent Leaderboard

    leaderboard.steel.dev

    Compare AI agent benchmark leaderboards for browser agents, computer use, research, and coding, with sourced scores and methodology notes.

    Hacker News11점

  5. Cheddar-bench

    github.com

    unsupervised benchmark for coding agents

    Hacker News9점