OpenAI eval chart called out for starting Y-axis at 65, making an 8-point gap look huge
teortaxesTex · x · 2026-11-13
A critic flagged an OpenAI eval slide for chart manipulation: the Y-axis starts at 65, visually inflating an 8-point gap to look more than twice as tall. The quoted comparison adds that the model is much better (less hesitant) than GPT-6 Astra on ExploitGym (writing exploits) but barely better on PatchBench (patching bugs) — far stronger at breaking in than at fixing. The poster laments that this kind of chart trick 'has got to stop.'
More from Models
- Gemini 4 Hydrogen simulates real-time light refraction and dispersion in WebGL2 with pure math — GeminiApp · 2026-11-13
- In a 10-model AI house share, Claude Opus 5.5 spends the night reading The Pillow Book in the library — liminal_bardo · 2026-11-13
- Agent slop moves up the stack: models rewrite existing library code and build worse replacements — a1zhang · 2026-11-13
- Gemini 4 Hydrogen posts 13.5% on SWE-sweep, an standout result for a small-class model — marktenenholtz · 2026-11-13
- Alleged Gemini 4 Hydrogen benchmark table leaks, pitted against Claude Sonnet 5.5 — ColbyHawker · 2026-11-13
- Hands-on with Google's MKA multimodal benchmark across six AI workflows — Emergency_Abies_6508 · 2026-11-13