GPT-5.1 Codex Mini — benchmark results

OpenAI's compact Codex-specialized GPT-5.1 tier. Provider: OpenAI. Released 2025-11-19. Access: API.

Unified ELO 1610 ± 45, rank #458 of 1776 rated models, from 18 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SnakeBench36.5TrueSkill Rating99.1
AI Chess Leaderboard (Reasoning)952Elo80.6
AA-LCR62.7Score (self-reported)79.7
Terminal-Bench 2.061.6Accuracy (%)75.9
AI Chess Leaderboard (Continuation)812Elo73.3
BenchTable56.5Total Score (%)65.1
Design Arena (Game Dev)1151Elo37.1
Design Arena (Website)1138Elo32.7
Design Arena (UI Components)1122Elo31.6
CritPt0Accuracy (self-reported)30.3
Design Arena (Data Viz)1133Elo29
Arena AI Code1239Arena ELO (self-reported)15.9

Interactive version: theaggregate.ai/model?slug=gpt-5-1-codex-mini · How the rankings work · Data refreshed daily, snapshot 2026-07-22.