OpenAI: GPT-5.1-Codex-Mini

OpenAI's GPT-5.1-Codex-Mini, a smaller and faster iteration of GPT-5.1-Codex, demonstrates competitive response times, ranking in the 56th percentile across benchmarks. It offers moderate pricing, positioned in the 21st percentile. Notably, the model exhibits exceptional reliability, achieving a 100% success rate across all evaluated benchmarks, indicating consistent operational stability. The model excels in several key areas. It achieved perfect accuracy in both General Knowledge and Ethics, with the former also being the most accurate at its price point and among models of similar speed. Its Mathematics performance is outstanding, reaching 96.0% accuracy and ranking as the most accurate among models of comparable speed. Instruction Following and Reasoning also show strong results, with 79.0% and 98.0% accuracy respectively, placing them in the 92nd and 93rd percentiles. Coding performance is robust at 92.0% accuracy. While its Hallucinations accuracy is 94.0%, it falls in the 49th percentile, suggesting room for improvement in acknowledging uncertainty. Email Classification is solid at 98.0% accuracy. The model generally maintains competitive costs across most benchmarks, particularly in Instruction Following, Reasoning, and Coding.