Grok 4.5 Ties Competitor on Coding Benchmark
elonmusk · x · 2026-07-11
Grok 4.5 paired with Grok Build has tied with Codex GPT-5.6 on the SWE-Atlas-QnA benchmark, scoring 84. The repost describes this as another leap forward for xAI in coding and agentic capabilities, noting that this feature is now accessible via the new Meta Model API and Meta AI.
Related event: Grok 4.5 Tops Coding Benchmark with High Token Efficiency(3 posts)→
More from coding & agent
- Multiagent v2 playbook calls for 64 agents, diverse proof routes and adversarial checks — danshipper · 2026-07-21
- Hermes Agent adds built-in Word, Excel, PDF and PowerPoint support — Teknium · 2026-07-21
- Super Proxy open-sources a self-hosted multi-provider LLM gateway with fallback and cost caps — Delicious-Flan88 · 2026-07-21
- Open-source MCP server connects Screener.in to live financial data for LLM research workflows — ashutosh_811 · 2026-07-21
- Marker 2 launches with PDF-to-Markdown support and claims up to 27 pages/sec — VikParuchuri · 2026-07-21
- Belgie lets Python developers build React MCP apps without installing Node.js — TheRealMrMatt · 2026-07-21