Claude Opus 5.5 leads intelligence ranking

Claude Opus 5.5 leads modelgrep’s October 2026 ranking with a score of 58.4 on the Artificial Analysis Intelligence Index. GPT-6 Astra follows at 56.9, ahead of GPT-6.1 Sol at 54.5. The index combines reasoning, knowledge, math and science benchmarks to compare large language models.

The ranking covers 25 models and includes pricing, generation speed, latency and capability indicators alongside intelligence scores. Claude Sonnet 5.5 scores 54.2, followed by GPT-6.1 Terra at 51.0 and Gemini 4 Argon at 50.4. Other entries include Claude Fable 5.1 at 49.0, Kimi K3.1 Pro at 46.0 and Meta’s Muse Wonder at 43.3.

Among models marked open, DeepSeek V4.1 Flash 1017 scores 32.5, while GLM 5.3 scores 31.7. The comparison identifies GPT-6 Astra as the closest alternative to the leader specifically on the intelligence metric, with separate speed and pricing data available to assess other tradeoffs.