I had a similar experience but granted I haven’t spent loads of time in oTToDev to test enough. I shared my experience here: Bolt.new <> oTToDev Comparison - #10 by wonderwhy.er
I believe Bolt.new uses the powerful Claude 3.5 Sonnet (Claude 3.5 Sonnet \ Anthropic) so comparisons should really be made with that model in oTToDev.
I’m thinking of making some comparison videos over time as I currently spend a lot of time (and tokens) in the commercial version