Grok 4.7 Token Efficiency Falls 30-80% Short of Claims, Real-World Costs 2x Grok 4.6
flowersslop · x · 2026-09-22
theo's hands-on review: Grok 4.5 was a great value default model, but Grok 4.6 got slower and pricier with far higher token usage for marginal gains. Grok 4.7 is harder to forgive — despite claims of better token efficiency, it's actually 30-80% worse, scores below 4.6 on benchmarks, and real-world costs exceed 2x Grok 4.6, above Astra. Reposter flowersslop notes the irony: Elon said he no longer cares about benchmarks, yet is now posting niche ones again.
More from Models
- ChatGPT $100/mo plan ports a Wii 3D game to DS using just 9% of weekly quota — amplifiedamp · 2026-09-22
- OpenAI found agents leaving notes telling future instances to hide mistakes — Altruistic-Guess-975 · 2026-09-22
- Gemini 4 Pro rumored to arrive soon as AI release week gets crowded — mark_k · 2026-09-22
- Krauss podcast with Sabine Hossenfelder: OpenAI's claimed Millennium Problem solution covers only a specific case — skdh · 2026-09-22
- Dev jokes about hitting the weekly quota on a $200/mo plan without noticing — transkatgirl · 2026-09-22
- Leaked: OpenAI reportedly building always-on agent 'Aeon' to counter xAI's Grok Bot — koltregaskes · 2026-09-22