Gemini 4 Argon Takes SimpleQA Verified Crown at 76%, Ending OpenAI's Streak
zacharynado · x · 2026-10-14
On SimpleQA Verified (1,000 world-knowledge factoid questions, 90 models tested), Google DeepMind's Gemini 4 Argon (high) is the new SOTA at 76.0%±1.4%, edging out OpenAI's GPT-6 Astra (75.6%) and GPT-6.1 Sol (73.9%); Gemini 3.1 Pro and Claude Opus 5.5 trail at 73.5% and 72.2%. The poster notes the benchmark matches their vibes-based judgment well and that Gemini 3.1 Pro held the top spot for 7 months before GPT-6 Astra briefly dethroned it.
More from Models
- Opus 5.5 still leads a month later, but open-weight decision models are closing in — airesearch12 · 2026-10-16
- Google restricts Gemini Pro access for Google Plus subscribers, matching free tier — EmergencyLess8861 · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta open-sources Muse Spark: runs on two Mac Studios, license bans passing output off as human-written — mawcopolow · 2026-10-16
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16