HN Explorer

ibragim_bad

↗ HN profile [ 33.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Opus 5.5 vs. GPT-6 in pi-agent: reasoning efforts and DeepSeek, GLM, Qwen (ibragim.dev)
    2 points 0
  2. 13 Models and 4 Agents on SWE Tasks: Go, Java, Python, Rust, TS (swe-rebench.com)
    51 points 15
  3. SWE-Rebench (December 2025) (swe-rebench.com)
    1 points 0
  4. SWE-rebench: Over 21,000 Open Tasks for SWE LLMs (huggingface.co)
    5 points 1