Benchmark,Gemini 4 Argon,GPT-6 Astra,Claude Fable 5.1,Claude Opus 5.5,Fuente,Consulta Vals Index,68.9,63.1,65.8,67.0,https://deepmind.google/models/gemini/,2026-10-01 AutomationBench,51.3,41.4,31.4,42.5,https://deepmind.google/models/gemini/,2026-10-01 DeepSWE v1.1,77.9,74.1,67.4,74.2,https://deepmind.google/models/gemini/,2026-10-01 FrontierSWE v2,55.0,65.5,56.3,62.3,https://deepmind.google/models/gemini/,2026-10-01