Rant: Gaming AI Model Benchmarks with Custom Metrics
JJitsev · x · 2026-07-13
The author rants about the current chaos in AI model evaluation: making one's own model look the strongest by inventing scoring metrics that no one else uses. For example, in the SOOFI evaluation, using a so-called "capability index" to evaluate base models made Qwen 3 32B appear weaker than practically insignificant models like Teuken.
Related event: Controversy Over Nemotron Reproduction and Custom Benchmarks(4 posts)→
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11