Satire: Grok 4.6 Matches Claude Fable 5 on WANDR at One-Third the Cost
elonmusk · x · 2026-08-14
Elon Musk shared a satirical benchmark review filled with fictional model names. The tweet claims that on Perplexity's WANDR benchmark, Grok 4.6 matched Claude Fable 5 with a score of 0.496, but at a fraction of the cost ($7.58 vs $20.30 per task), while also outperforming GPT-5.6 Sol.
This is a humorous jab by the AI community at the constant benchmark racing, version number inflation, and pricing wars among current LLMs.
Related event: Grok 4.6 tops real-world coding benchmarks with standout cost efficiency(10 posts)→
More from Fun
- Sabine Hossenfelder fires back: academia's impact metric turned physics into a paper mill — skdh · 2026-10-16
- Meme: Clicking 'Yes to all' on Claude Code without reading anything — jnack · 2026-10-16
- Minecraft AI mod turns region selection + prompts into autonomous building agent — Acclynn · 2026-10-16
- Throwaway prop code in movies is getting eerily accurate, and AI is why — mike64_t · 2026-10-16
- Distillation copies logits, not hidden CoT — open-sourcing 1.3 leaks IP, not reasoning data — teortaxesTex · 2026-10-16
- Scott Aaronson's 9-year-old son: "I don't think problems should be independent of the axioms" — basedjensen · 2026-10-16