Unverified50% confidenceBenchmarkExact time
In an official benchmark test run on AWS EC2 with 500 concurrent users over 60 seconds, Bifrost achieved 424 requests/second while LiteLLM achieved 44.84 requests/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedAWS在2017年率先将EC2实例从按小时计费改为按秒计费，最低60秒71% similarUnverifiedIn this test, when the 7900XTX is run with a 256K context, a single generation takes up to 743 seconds.67% similarUnverifiedIn the long-context archiving experiment, 8 requests each input approximately 261,000+ tokens and each completed approximately 1,022 outputs; the total throughput of the joint decoding window was 214.85 tokens per second, approximately 26.86 per request, but the window was only approximately 2.28 seconds and prefilling was serial or interleaved.66% similarUnverifiedThe MiMo V2.6 Pro cluster runs a hello test at approximately 15 tokens/second, dropping to approximately 12 tokens/second for complex tasks.66% similarUnverifiedDuring an 8,000-token run, Ollama reported a duration of 125 seconds, while the client actually waited 725 seconds, with the difference being gateway queuing time that is invisible to the server-side numbers.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004563API
curl https://kongchang.com/api/v1/knowledge/claims/1004563MCP
get_claim(id=1004563)