Bakeoff

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

13:16

2026-09-24

ariwilson.com

ai-agents

The same bug fix costs 0.4¢ or $2, depending on which coding agent you ask

A private coding-agent evaluation called Bakeoff recorded 277 runs across 10 harness-and-model combinations, spanning 10 models and 3 harnesses (Claude Code, Codex CLI, and pi) at an approximate cost …

00:00

2026-09-10

ariwilson.com

ai-research

Next steps for me: Bakeoff

A laid-off engineering executive built Bakeoff, a private evaluation that runs real bugs from his own codebases through the latest OpenAI and Anthropic models in their own harnesses plus GLM in pi, sc…

// co-occurs with top 8 entities

pi 2 Anthropic 2 OpenAI 2 Claude Code 1 Codex CLI 1 Go 1 GLM 1 VideoAmp 1

// topics top 6 topics

ai agents 2 ai tools 2 large language models 2 developer tools 1 ai products 1 ai research 1