Personal LLM leaderboards are valuable precisely because they aren't benchmaxxed
teortaxesTex · x · 2026-11-13
teortaxesTex argues he values personally maintained LLM leaderboards because, representative or not, they surely aren't intentionally benchmaxxed — and this particular ranking's profile actually makes sense: less "make the user happy" and more specified-task performance. He adds that he suspects @aquilesfd has to keep reading fresh reports on benchmark cheating to see how models game his tests.
Related event: Developer Builds Personal Coding Benchmark Testing 19 Models on 21 Tasks(2 posts)→
More from Models
- AI Daily: Huang resigns, Anthropic IPO at up to $1.4T, Gemini 4 Carbon opens — xiaohu · 2026-11-13
- Dylan Patel: Moonshot and DeepSeek's open-source code only targets Blackwell — anshulkundaje · 2026-11-13
- Tesla FSD handles a dark, snowy Finnish road and yields to a bus smoothly — yunta_tsai · 2026-11-13
- Claude now refuses to work on open-source projects that ban AI contributions — esrtweet · 2026-11-13
- Thinking Machines' Inkling 2 Small (594B MoE, 1M context) lands on Ollama — ollama · 2026-11-13
- No forensic evidence DeepSeek's V4.1-Flash used Blackwell, buried in report appendix — suchenzang · 2026-11-13