Grok reportedly triples Terminal-Bench score in two months, 12.4% to 38%, passing GPT-5.6 Sol
CurieuxExplorer · x · 2026-09-22
A widely shared post claims Grok jumped from 12.4% to 38.0% on Terminal-Bench 4.0 in just two months, tripling its score and overtaking GPT-5.6 Sol. The framing calls it a gear change rather than incremental progress. Note: this is third-party relay, not officially confirmed.
Related event: Grok triples Terminal-Bench score in two months(3 posts)→
More from Models
- Open-source Laya classifies with calibrated probabilities in a single 33ms pass — minchoi · 2026-09-22
- Musk shows Grok 4.7 doing real engineering at Tesla, shipping FSD features overnight — elonmusk · 2026-09-22
- Dev Praises Qwen3.8-max-preview xhigh, Ran Workloads Nearly 24 Hours on Generous Quota — jasonkneen · 2026-09-22
- Musk Announces Grok 4.7, Cited Demo Builds Interactive 3D Jet Engine in Minutes — elonmusk · 2026-09-22
- GPT-6 Sol, Luna and 'Astra Minor' reportedly spotted in Azure model config — 141_1337 · 2026-09-22
- $40M-backed Jev got an open-source API clone within three days — Nickabot · 2026-09-22