GPT-4: A Year of Reign Against Fleeting Models
Le brief IA que les pros lisent chaque soir
Les 7 actus IA du jour, décryptées en 5 min. Gratuit.
Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.
Choisis ton rythme
Gratuit · Pas de spam · Désabonnement en 1 clic
GPT-4: A One-Year Reign Against Ephemeral Models
OpenAI's GPT-4 has held the top spot in the Epoch Capabilities Index (ECI) for about a year. The ECI is a composite measure of language model performance. According to Epoch AI researcher Jaeho Lee, this duration is significantly longer than that of any other model since. OpenAI's o1 model held the second-longest lead with just over three months, which is less than a third of GPT-4's reign. Since Claude 3 Opus dethroned GPT-4 in February 2024, the top position has changed hands 17 times. The median duration at the top for each model was around seven weeks.
The graph can be interpreted in two ways. It shows how long competing labs needed to match GPT-4, a true anomaly at its launch. But it also indicates that competition has become much fiercer since then. No model can now maintain a comparable lead, and the jumps in capability between transitions are faster but smaller compared to GPT-4 and the era that began with reasoning models like o1-preview in the fall of 2024.
Brief IA — L'actualité IA en français
L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.