Learn extra at:
“GPT‑4.1 mini is a big leap in small mannequin efficiency, even beating GPT‑4o in lots of benchmarks. It matches or exceeds GPT‑4o in intelligence evals whereas decreasing latency by almost half and decreasing value by 83%,” the announcement mentioned. “For duties that demand low latency, GPT‑4.1 nano is our quickest and least expensive mannequin out there. It delivers distinctive efficiency at a small measurement with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding—even larger than GPT‑4o mini. It’s ideally suited for duties like classification or autocompletion.”
These enhancements, OpenAI mentioned, mixed with primitives such because the Responses API, will permit builders to construct extra helpful and dependable brokers that can carry out complicated duties akin to extracting insights from massive paperwork and resolving buyer requests “with minimal hand-holding.”
OpenAI additionally mentioned that GPT-4.1 is considerably higher than GPT-4o at duties akin to agentically fixing coding duties, front-end coding, making fewer extraneous edits, following diff codecs reliably, making certain constant device utilization, and others.
