{"slug": "grok-4-5-ranks-second-on-apex-swe-leaderboard-as-ai-coding-race-heats-up", "title": "Grok 4.5 ranks second on APEX-SWE leaderboard as AI coding race heats up", "summary": "XAI's Grok 4.5 ranked second on the Mercor APEX-SWE leaderboard with a 51.2% Pass@1 accuracy, trailing Anthropic's Claude Fable 5 at 65.5%. The benchmark tests real-world software engineering tasks, highlighting the intensifying competition among AI coding models.", "body_md": "# Grok 4.5 ranks second on APEX-SWE leaderboard as AI coding race heats up\n\nxAI's latest model hits 51.2% Pass@1 accuracy but trails Anthropic's Fable 5 by a significant margin in real-world software engineering tests\n\nThe AI coding benchmark wars just got a new entry, and the scoreboard is already reshaping how enterprises think about which models to deploy. xAI’s Grok 4.5 has secured second place on the Mercor APEX-SWE leaderboard, posting a 51.2% Pass@1 accuracy score. That sounds impressive until you look one row up and see Anthropic’s Claude Fable 5 sitting at 65.5%.\n\n## What APEX-SWE actually measures\n\nAPEX-SWE was launched in March 2026 by Mercor in collaboration with Cognition. The benchmark focuses specifically on real-world production software engineering tasks, with particular emphasis on integration work and observability challenges, testing whether a model can do the kind of messy, interconnected coding work that actual engineering teams deal with every day.\n\nFable 5, released in early June 2026 and optimized specifically for high-capability reasoning and agentic tasks, leads the board at 65.5% plus or minus 6.2%. Grok 4.5 sits at 51.2% plus or minus 6.0%.\n\n## Grok 4.5’s case for itself\n\nGrok 4.5, which launched in early July 2026, secured the top ranking on AutomationBench-AA with a 51% score, a separate benchmark that evaluates automation capabilities across agentic workflows.\n\nxAI has positioned Grok 4.5 as delivering comparable results to competitors at a cost-per-task that is 4 to 17 times lower, depending on the workload.\n\nThe absence of blockchain-specific evaluation criteria in APEX-SWE also points to a gap that has not been filled. Real-world software engineering benchmarks have not yet incorporated the specific complexity of Solidity development, cross-chain integration testing, or on-chain state management as distinct evaluation categories.\n\n**Disclosure:** This article was edited by Editorial Team. For more information on how we create and review content, see our\n\n[Editorial Policy](https://cryptobriefing.com/editorial-policy/).", "url": "https://wpnews.pro/news/grok-4-5-ranks-second-on-apex-swe-leaderboard-as-ai-coding-race-heats-up", "canonical_source": "https://cryptobriefing.com/grok-45-apex-swe-leaderboard-second-fable-5/", "published_at": "2026-07-11 05:36:03+00:00", "updated_at": "2026-07-11 05:44:15.083556+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products"], "entities": ["xAI", "Grok 4.5", "Anthropic", "Claude Fable 5", "Mercor", "Cognition", "APEX-SWE"], "alternates": {"html": "https://wpnews.pro/news/grok-4-5-ranks-second-on-apex-swe-leaderboard-as-ai-coding-race-heats-up", "markdown": "https://wpnews.pro/news/grok-4-5-ranks-second-on-apex-swe-leaderboard-as-ai-coding-race-heats-up.md", "text": "https://wpnews.pro/news/grok-4-5-ranks-second-on-apex-swe-leaderboard-as-ai-coding-race-heats-up.txt", "jsonld": "https://wpnews.pro/news/grok-4-5-ranks-second-on-apex-swe-leaderboard-as-ai-coding-race-heats-up.jsonld"}}