{"slug": "was-lucky-to-have-tested-fable-5-on-chess-bench", "title": "Was lucky to have tested fable 5 on chess-bench", "summary": "A new chess benchmark, chess-bench, ranks AI models by performance, with Gemini 3.5 Flash leading at 61.3%, followed by Grok 4.1 Fast at 58.7% and Gemini 3.1 Pro Preview at 55.3%. The test included Claude Fable 5, which scored 46.0%, ranking ninth. The benchmark highlights significant performance gaps among leading AI models.", "body_md": "| Rank | ||\n|---|---|---|\n#1 | Gemini 3.5 Flash | 61.3% |\n#2 | Grok 4.1 Fast | 58.7% |\n#3 | Gemini 3.1 Pro Preview | 55.3% |\n#4 | Grok 4.20 | 54.7% |\n#5 | Grok 4.20 Beta | 53.3% |\n#6 | Grok 4.3 | 48.7% |\n#7 | Gemini 3 Flash Preview | 48.7% |\n#8 | Gemini 3.1 Flash Image Preview | 46.0% |\n#9 | Claude Fable 5 | 46.0% |\n#10 | GPT-5.4 | 32.7% |\n#11 | GPT-5.5 | 29.3% |\n#12 | Qwen 3.6 Plus | 28.0% |\n#13 | Claude Opus 4.8 | 24.0% |\n#14 | Qwen 3.6 Plus Preview | 22.0% |\n#15 | Claude Opus 4.7 | 18.7% |\n#16 | Claude Opus 4.6 | 16.7% |\n#17 | GLM 5.2 | 13.3% |\n#18 | GLM-5.1 | 12.7% |\n#19 | GLM-5 | 12.0% |\n#20 | Claude Sonnet 4.6 | 10.7% |\n#21 | Claude Haiku 4.5 | 8.7% |\n#22 | Gemini 2.5 Pro | 5.3% |", "url": "https://wpnews.pro/news/was-lucky-to-have-tested-fable-5-on-chess-bench", "canonical_source": "https://www.chess-bench.com", "published_at": "2026-06-20 17:25:02+00:00", "updated_at": "2026-06-20 17:37:03.343162+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-products"], "entities": ["Gemini", "Grok", "Claude", "GPT", "Qwen", "GLM", "Fable 5", "chess-bench"], "alternates": {"html": "https://wpnews.pro/news/was-lucky-to-have-tested-fable-5-on-chess-bench", "markdown": "https://wpnews.pro/news/was-lucky-to-have-tested-fable-5-on-chess-bench.md", "text": "https://wpnews.pro/news/was-lucky-to-have-tested-fable-5-on-chess-bench.txt", "jsonld": "https://wpnews.pro/news/was-lucky-to-have-tested-fable-5-on-chess-bench.jsonld"}}