GPT-3.5 Turbo (1106) — benchmark results

November 2023 GPT-3.5 Turbo API snapshot (gpt-3.5-turbo-1106). Provider: OpenAI. Released 2023-11-06. Access: API.

Unified ELO 1460 ± 27, rank #957 of 1776 rated models, from 35 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
T-Eval84Overall Score (%)95
OpenBookQA86Accuracy (%)92.9
ARC Challenge (AI2)87.4Accuracy (%)91
LogicKor - Grammar7.92Score (0-10)90.7
SpeechMap Compliance89.5% Requests Completed89.1
LogicKor - Math7.57Score (0-10)88.1
TriviaQA85.8Accuracy (%)87.2
Epoch AI - Adversarial Nli58.1Score86.4
LogicKor - Multi-Turn7.88Score (0-10)83.4
LogicKor7.79Score (0-10)83.2
VNTL Leaderboard69.98Accuracy (%)82.6
LogicKor - Coding9.07Score (0-10)82.3

Interactive version: theaggregate.ai/model?slug=gpt-3-5-turbo-1106 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.