Grok triples Terminal-Bench score in two months

xAI's Grok 4.7 model card shows its Terminal-Bench 4.0 score tripled from 12.4% to 38.0% in two months, surpassing GPT-5.6 Sol, though Claude Fable 5.1 still leads at 57.9%.

2026-09-22 ~ 2026-09-22 · 3 related posts

• Grok 4.7 model card: Terminal-Bench 4.0 score jumps from 20.3% to 38.0%, still trails Claude Fable 5.1 — ns123abc · 2026-09-22
• Grok triples Terminal-Bench 4.0 score in two months, overtakes GPT-5.6 Sol — ns123abc · 2026-09-22
• Grok reportedly triples Terminal-Bench score in two months, 12.4% to 38%, passing GPT-5.6 Sol — CurieuxExplorer · 2026-09-22