Unverified50% confidenceFactExact time
The 91% performance figure comes from Bolt's internal benchmarks, not from independent third-party evaluations.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/19/2026
First Seen
Valid until: 12/18/2026
Sources
Related Entities
Related Claims
UnverifiedThe per-step accuracy of current top-tier models is approximately between 90% and 95%.61% similarUnverifiedThe human baseline accuracy is 90.8%.59% similarUnverifiedProfit margins for model vendors on inference are reportedly as high as 70%–90%.58% similarUnverifiedAccording to The Wall Street Journal, Google's internal evaluation showed that these intermediate checkpoint models had no significant performance advantage over the Flash series.58% similarUnverifiedA confidence score given by a model (e.g., 90%) should not be interpreted as 'the model is correct 90% of the time'; accuracy must be empirically measured using your own samples.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/935507API
curl https://kongchang.com/api/v1/knowledge/claims/935507MCP
get_claim(id=935507)