The Darwin-36B-Opus model, a 36-billion-parameter mixture-of-experts language model, has been released. It was created using the Darwin V7 evolutionary breeding engine, combining aspects of Qwen/Qwen3.6-35B-A3B and a Claude 4.6 Opus distilled variant. This automated process produced a deployable checkpoint in under an hour on a single GPU. Darwin-36B-Opus achieved an 88.4% score on the GPQA Diamond benchmark, setting a new record for the Darwin family's open models. AI
Summary written by None from 1 source. How we write summaries →
IMPACT New open-source model demonstrates state-of-the-art performance on graduate-level science questions.
RANK_REASON Release of a new open-source language model with benchmark results.
