Grok 4.7 model card shows Terminal-Bench jumping 20.3% to 38% at the same price as 4.6
elonmusk · x · 2026-09-22
Elon Musk retweeted the Grok 4.7 model card, highlighting sizable benchmark jumps over 4.6:
- Terminal-Bench: 20.3% → 38.0%
- SWE-Marathon: 31.9% → 46.0%
- HealthBench Pro: 48.5% → 56.7%
- Legal Agent: 15.8% → 19.6%
- EEBench: 60.0% → 66.0%
All at the same price as 4.6, with the biggest gains in coding and terminal agent tasks.
More from Models
- Gemini 4 Carbon opens to all at $2/$10, price doubling to $4/$20 on Dec 1 — socialwithaayan · 2026-11-12
- Gemini 4 Carbon reportedly drops as builders share 10 early wild examples — socialwithaayan · 2026-11-12
- How to cut Fable 5.2 token costs by 90%: Arc routing plus a lean CLAUDE.md — EXM7777 · 2026-11-12
- Grok Bot 1.0 launches with support for joining Meet, Zoom and Teams calls — mark_k · 2026-11-12
- Partial RuneBench results: Inkling 2 Small scores 5.314, far above original — mariofilhoml · 2026-11-12
- Grok Bot 1.0 Announced: Shareable Bots With Upgraded Collaboration — SpaceXSI · 2026-11-12