Elon Musk on Grok 4.5 Performance
elonmusk · x · 2026-07-13
Elon Musk stated that the publicly available version of Mythos (Fable, with Claude as a fallback) is "noticeably nerfed," though it's the only version most people can access right now.
He added that Grok 4.5 is slightly higher than Fable on some software benchmarks, and that Fable itself is already a "very good model."
Related event: Musk Says Grok 4.5 Beats Fable on Some Coding Benchmarks(3 posts)→
More from Models
- Frontier models can one-shot grad-level tasks — if the prompt and context are right — MoonL88537 · 2026-07-22
- Current setup is 8,192 input tokens and 2,048 output tokens, with 8k/512 next — TheZachMueller · 2026-07-22
- Gemini 3.6 Flash is pitched as cheaper and more token-efficient, but developers say coding has worsened — techartist_ · 2026-07-22
- Kimi K3 feels slower than K2.7, but stronger on long coding jobs and refactoring — Far-Presence2711 · 2026-07-22
- Poolside launches Laguna S 2.1 with 118B parameters and 8B active per token — Madisonkanna · 2026-07-22
- OpenWiki adds Gemini AI Studio, Vertex AI, and new Flash models — BraceSproul · 2026-07-22