Semi-Analysis
An independent technical research firm specializing in semiconductors and data centers. It publishes industry research reports and develops benchmarking tools for analyzing hardware and infrastructure in the AI and computing sectors.
Timeline (last 90 days)
OpenAI used Semi-Analysis's public benchmark InferenceX to test Jalapeño on three open models: GPT-OSS 120B, DeepSeek R1 670B, and Kimi K2 1T.
The core metric of InferenceX is the latency-throughput trade-off curve, which measures the number of requests a system can handle and its energy consumption under the constraint of a set maximum acceptable response latency for users.
All Facts (2)
OpenAI used Semi-Analysis's public benchmark InferenceX to test Jalapeño on three open models: GPT-OSS 120B, DeepSeek R1 670B, and Kimi K2 1T.
50%UnverifiedThe core metric of InferenceX is the latency-throughput trade-off curve, which measures the number of requests a system can handle and its energy consumption under the constraint of a set maximum acceptable response latency for users.
50%