Unverified50% confidenceBenchmarkExact time
In this test, Bolt scored 100, went from prompt to launch in about 6 minutes, required 0 fix prompts, and consumed about 101K of 1 million monthly tokens on the free tier.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedIn the FlappyBit Extreme game generation task, the model thought for about 91000 tokens, inference speed dropped to 15 tok/s, and it finally completed the output at 105000 tokens after about 2 hours.64% similarUnverifiedDifferent evaluation methods have different execution latency and cost per 100 runs: exact string matching <1 millisecond/$0.00, Pydantic/JSON Schema 2-10 milliseconds/$0.00, semantic embedding distance 20-80 milliseconds/$0.001, small model grader 400-900 milliseconds/$0.02, frontier model grader 1-3 seconds/$0.40, human expert review hours to days/>$50.00.62% similarUnverifiedThe 30-day checkpoint for the experiment is October 22, with targets of 5 user testimonials and 100 free installs, while the current counts are 0 and 062% similarUnverifiedAfter registering with WorkBuddy you receive 2000 credits, and afterwards you can actively claim 100 credits per day; credits do not arrive automatically and do not accumulate.62% similarUnverifiedThe author considers a model usable only if it achieves at least 10 tokens per second.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060625API
curl https://kongchang.com/api/v1/knowledge/claims/1060625MCP
get_claim(id=1060625)