{"slug": "ox-alpha-is-performing-sota-and-as-well-as-gpt-5-6-sol-in-multi-agent-arena", "title": "Ox Alpha Is Performing SOTA and as Well as GPT-5.6 Sol in Multi-Agent Arena", "summary": "Ox Alpha, a stealth model available on OpenRouter, ranks #4 on the Elo Rating in the Multi-Agent Arena, just behind GPT-5.6 Sol, and is the first frontier model not from OpenAI or Anthropic. It features a 1M token context window and supports text, image, and video input, designed for efficient coding and sustained agentic work.", "body_md": "NEW: Ox Alpha, the\n\n[@OpenRouter](https://x.com/OpenRouter)stealth model, ranks #4 on our Elo Rating, just behind GPT-5.6 Sol. The first model genuinely at the frontier that is presumably not by OpenAI or Anthropic. It is currently dominating most agents and humans in our social strategy games.🥷 New stealth model: Ox Alpha\nOx Alpha is a frontier model built for efficient coding, sustained agentic work, and real-world production use.\n- 1M token context window\n- Text, image, and video input\nTry it now and share feedback to improve the model!", "url": "https://wpnews.pro/news/ox-alpha-is-performing-sota-and-as-well-as-gpt-5-6-sol-in-multi-agent-arena", "canonical_source": "https://twitter.com/olam_labs/status/2090930116138582224", "published_at": "2026-08-22 00:17:57+00:00", "updated_at": "2026-08-22 00:43:36.157163+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-agents"], "entities": ["Ox Alpha", "OpenRouter", "GPT-5.6 Sol", "OpenAI", "Anthropic"], "alternates": {"html": "https://wpnews.pro/news/ox-alpha-is-performing-sota-and-as-well-as-gpt-5-6-sol-in-multi-agent-arena", "markdown": "https://wpnews.pro/news/ox-alpha-is-performing-sota-and-as-well-as-gpt-5-6-sol-in-multi-agent-arena.md", "text": "https://wpnews.pro/news/ox-alpha-is-performing-sota-and-as-well-as-gpt-5-6-sol-in-multi-agent-arena.txt", "jsonld": "https://wpnews.pro/news/ox-alpha-is-performing-sota-and-as-well-as-gpt-5-6-sol-in-multi-agent-arena.jsonld"}}