GPT-4.1 Nano — benchmark results

OpenAI's smallest, fastest, cheapest GPT-4.1 tier, keeping the family's 1M-token context for low-latency classification and autocomplete. Provider: OpenAI. Released 2025-04-14. Access: API.

Unified ELO 1452 ± 5, rank #983 of 1776 rated models, from 946 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
OpenVLM MMT-Bench - One Shot Detection95Score (%)99
EuroEval Dutch Simplification - Duidelijke Taal57.78Score (%)98.9
OpenVLM MMT-Bench - Furniture Keypoint Detection75Score (%)98.5
OpenVLM MMT-Bench - CIM76.7Score (%)97.3
OpenVLM MMT-Bench - Traffic Light Understanding100Score (%)96.4
EuroEval Bosnian56.05Average Score (%)94.8
OpenVLM MMT-Bench - Point Tracking85Score (%)93.9
OpenVLM MMT-Bench - Clock Reading75Score (%)93.7
OpenVLM MMMU - Chemistry66.7Accuracy (%)92.6
OpenVLM MMT-Bench - Traffic Participants Understanding65Score (%)92.5
EuroEval Icelandic NLU - Hotter and Colder Sentiment55.79Sentiment classification Score (%)92.3
OpenVLM MMMU - Finance76.7Accuracy (%)91.7

Interactive version: theaggregate.ai/model?slug=gpt-4-1-nano · How the rankings work · Data refreshed daily, snapshot 2026-07-22.