Opinion page / measured product / rank 6
Bolt.new Reviews and Ratings (2026)
Reader ratings for Bolt.new, aggregated on the same 0 to 100 scale we use for the lab index, with our own commentary underneath. If you are looking for Bolt.new opiniones, reviews or a rating you can check, the measurements behind every claim are on the Bolt.new benchmark page.
Reader index
77.49
3 voters, 27 axis scores. Never blended into the lab index.
Lab index
74.68
Measured on the vibeOps spec
Strict pass rate
80.0%
36 clean and 1 failed executions
Median turn latency
82.1 s per prompt
p90 136.0 s
Reader index
One score per reader per axis on a 0 to 100 scale, editable at any time.
Reader index
77.49
Lab index
74.68
3 readers, 27 axis scores, last change 26 Aug 2026. Readers rate Bolt.new 2.8 points above the measurement.
Seeded at launch
The reader scores, lab notes and open ratings published here were written by this lab in August 2026 to populate the reader column before the site had readers. They are not customer submissions, they are not vendor supplied and nobody was paid for them. Anything submitted since then comes from a registered account. The lab index is measured from logged runs and is unaffected either way.
| Axis | Weight | Lab | Readers | Votes | Reader mean |
|---|---|---|---|---|---|
| Agent performance | 18% | 81.0 | 90.0 | 3 | |
| Reliability | 18% | 80.0 | 86.0 | 3 | |
| Scalability | 13% | 70.0 | 70.5 | 2 | |
| SEO and GEO | 12% | 66.0 | 70.7 | 3 | |
| API and MCP | 9% | 58.0 | 65.0 | 2 | |
| Integrations | 8% | 72.0 | 76.3 | 3 | |
| Design output | 7% | 85.0 | 89.7 | 3 | |
| Turn latency score | 7% | 79.4 | 44.0 | 3 | |
| Value | 5% | 71.0 | 79.7 | 3 | |
| Code ownership | 3% | 88.0 | 95.5 | 2 |
The reader index is a weighted mean of reader submitted axis scores using the published index weights, renormalised over the axes readers have scored. It is never blended into the lab index. How this works.
Score Bolt.new
Your scores feed the reader column only. Submitting an axis again edits your existing score rather than adding a second vote.
Reader scores need an account so one person cannot vote twice. Create a reader account or sign in.
Reader scores are published in a separate reader index column. They never move the measured lab index.
Reader lab notes on Bolt.new
Written by readers with an account. Sorted by upvotes, then by date.
No reader lab notes yet. A note has to describe something you actually built, so the first one here is worth reading.
Write a lab note
What you built, what broke, what you measured. Short opinions belong in the open rating form further down.
Open rating distribution
Open ratings submitted without an account. Neither the lab index nor the reader index is part of this average.
| Band | Share | Ratings |
|---|---|---|
| 90 to 100 | 0 | |
| 80 to 89 | 1 | |
| 70 to 79 | 1 | |
| 60 to 69 | 0 | |
| 0 to 59 | 0 |
Lab commentary
Our reading of the numbers, kept separate from the reader ratings.
Very fast to a running artifact and the code that comes out is plain and portable, which is why it takes the highest code ownership score here. It burns tokens quickly on the longer prompts: two runs stalled mid way through prompt 6 and had to be recorded as partial because the allowance ran out before the job queue was finished.
On the measured axes, Bolt.new is strongest at code ownership with a subscore of 88.0 and weakest at api and mcp at 58.0. Because api and mcp carries 9 of the 100 index points, that weakness costs it roughly 3.78 points against a perfect result on that axis alone.
Reader ratings and lab measurements answer different questions. A reader rating carries the thing a harness cannot capture: whether the product was pleasant to work with over weeks, how support behaved, whether the bill matched the plan. The lab index carries the thing an opinion cannot: 45 timed executions of the same specification with the failures counted. Read them side by side and treat a large gap between the two as the interesting signal.
2 open ratings
Newest first, no account needed. Moderated for spam and vendor astroturfing, not for sentiment.
The code is genuinely yours
Chloe Martin, Agency developer | 27 Aug 2026 Lab seeded
83Exported the project and deployed it on our own infrastructure with no edits. That matters for client work.
Great first hour
Erik Lund, Indie developer | 21 Aug 2026 Lab seeded
77Very quick to something running. Token budget is the real constraint on a project this size.
Add an open rating
No account needed. For a score that counts toward the reader index, use the axis form above.