{"slug": "waddle-labs-says-waddle-1-tops-robocurve-robot-benchmark-with-a-score-of-81", "title": "Waddle Labs says Waddle-1 tops Robocurve robot benchmark with a score of 81", "summary": "Waddle Labs, a two-person Y Combinator startup based in San Francisco, announced on November 20 that its first robot-use agent, Waddle-1, scored 81 in Robocurve PBC evaluations, ahead of GPT-6.2 Astra at 65 and Dream-1 at 59. Waddle Labs said Waddle-1 controls bimanual robots on unseen tasks zero-shot, and Robocurve's public leaderboard separately lists GPT-6.2 Astra at 65.7% and Dream-1 at 59.5% on its RoboDojo-RC Tier 1 benchmark. Waddle Labs also opened a preview API for the agent.", "body_md": "# Waddle Labs says Waddle-1 tops Robocurve robot benchmark with a score of 81\n\n**The two-person YC startup says its cloud reasoning agent beat GPT-6.2 Astra and Dream-1 on bimanual tasks it had not seen before, and opened a preview API.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nWaddle Labs says its first robot-use agent, Waddle-1, scored 81 in Robocurve PBC (@robocurve) evaluations, ahead of GPT-6.2 Astra at 65 and Dream-1 at 59.\n\nThe San Francisco startup announced Waddle-1 in a thread on X on November 20th, saying the system controls bimanual robots on unseen tasks zero-shot. Robocurve's public leaderboard separately lists GPT-6.2 Astra at 65.7% and Dream-1 at 59.5% on its RoboDojo-RC Tier 1 benchmark, consistent with the rounded comparison figures in the announcement.…", "url": "https://wpnews.pro/news/waddle-labs-says-waddle-1-tops-robocurve-robot-benchmark-with-a-score-of-81", "canonical_source": "https://runtimewire.com/article/waddle-labs-says-waddle-1-tops-robocurve-robot-benchmark-with-a-score-of-81", "published_at": "2026-11-20 23:49:41+00:00", "updated_at": "2026-11-21 00:13:27.458440+00:00", "lang": "en", "topics": ["robotics", "ai-agents", "ai-startups", "ai-research"], "entities": ["Waddle Labs", "Waddle-1", "Robocurve PBC", "GPT-6.2 Astra", "Dream-1", "RoboDojo-RC Tier 1", "Y Combinator"], "also_reported_by": [], "takeaway": "Waddle Labs reports Waddle-1 at 81 on Robocurve evaluations versus 65 for GPT-6.2 Astra and 59 for Dream-1, with Robocurve's leaderboard listing Astra at 65.7% and Dream-1 at 59.5% on RoboDojo-RC Tier 1.", "recommendation": {"advice": "Benchmark robot-use agents on unseen bimanual tasks zero-shot and report scores against a public leaderboard like RoboDojo-RC Tier 1 so results are comparable across models.", "playbook": "evals-testing", "playbook_url": "https://wpnews.pro/playbooks/evals-testing"}, "alternates": {"html": "https://wpnews.pro/news/waddle-labs-says-waddle-1-tops-robocurve-robot-benchmark-with-a-score-of-81", "markdown": "https://wpnews.pro/news/waddle-labs-says-waddle-1-tops-robocurve-robot-benchmark-with-a-score-of-81.md", "text": "https://wpnews.pro/news/waddle-labs-says-waddle-1-tops-robocurve-robot-benchmark-with-a-score-of-81.txt", "jsonld": "https://wpnews.pro/news/waddle-labs-says-waddle-1-tops-robocurve-robot-benchmark-with-a-score-of-81.jsonld"}}