AI Radar
Support
LiveUpdated 2026-11-06 16:05 UTC

SlopCodeBench

SlopCodeBench is Community driven benchmark for measuring code erosion under iterative specification refinement.. It is ranked #4729 on the AI Radar, in Frontier models, first seen 27 days ago and shared in 1 post (415 views).

Visit scbench.ai

SlopCodeBench v1.0 · 36 problems · 196 checkpoints · 19 models SlopCodeBench A community benchmark measuring code erosion as agents iteratively extend their own solutions across checkpoints. leaderboard → docs paper code_search.py cp 1 · regex search + 6 6 loc + 1 import re + 2 + 3 def search ( pattern , files ) : + 4 for f in files : + 5 if re . search ( pattern , f . read_text ( ) ) : + 6 yield f 6 / 39 top 10 models full leaderboard → model isolated solve (% / 100) erosion (0–1) ↓ lower is better verbosity (0–1) ↓ lower is better 01 GPT 5.5 / Codex 28.1% 0.494 0.269 02 GPT 5.3-Codex / Codex 26.0% 0.644 0.336 03 GPT 5.4 / Codex 25.5%…

Alternatives to SlopCodeBench

SlopCodeBench in numbers

FAQ

What is SlopCodeBench?

Community driven benchmark for measuring code erosion under iterative specification refinement. It was first shared on X 27 days ago and is ranked #4729 on the AI Radar.

Is SlopCodeBench free?

Pricing is not stated on the page we read.

Who shared SlopCodeBench?

1 account on X, including @LucasSmaira, in 1 post totalling 415 views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.