OpenAI: GPT-5.1-Codex-Mini

GPT-5.1-Codex-Mini, released by OpenAI on November 13, 2025, is positioned as a smaller and faster iteration of GPT-5.1-Codex. This model demonstrates competitive response times, performing among the faster models with a 58th percentile ranking across various benchmarks. Its pricing is moderate, ranking in the 24th percentile. A standout feature is its exceptional reliability, achieving a 100% success rate across all 8 benchmarks, indicating minimal technical failures. In terms of performance, GPT-5.1-Codex-Mini exhibits remarkable accuracy in several key areas. It achieved perfect scores in General Knowledge and Ethics, with the former also being the most accurate model at its price point and speed. Its Reasoning and Mathematics capabilities are also very strong, scoring 98.0% and 96.0% respectively, placing it in the 91st and 94th percentiles. Instruction Following is another strength, with an 88th percentile accuracy. While its Hallucinations accuracy is 94.0%, placing it in the 48th percentile, this suggests some room for improvement in acknowledging uncertainty. Coding and Email Classification show solid performance at 92.0% and 98.0% accuracy respectively. Overall, the model's strengths lie in its high accuracy across knowledge, reasoning, and ethical tasks, coupled with its robust reliability.