GPT-3.5 Turbo Instruct: benchmark results

Provider: OpenAI. Released 2022-11-30. Access: API.

Unified ELO 1481 ± 48, rank #1273 of 2656 rated models, from 13 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI Chess Leaderboard (Continuation)1436Elo94.4
Chess Bench LLM1586Lichess Rating91.2
LM Market Cap LMC Score40LMC Score (0-100)28
Klu LLM Leaderboard70Klu Index27.5
AI Chess Leaderboard (Reasoning)553Elo22.8
AgentDrive - Physics27.5Accuracy (%)22
AgentDrive - Scenario82.5Accuracy (%)12
METR Benchmark0.0150% Time Horizon (hours)8
AgentDrive - Comparative52.5Accuracy (%)7
AgentDrive - Hybrid5Accuracy (%)7
AgentDrive34.5Accuracy (%)6
METR Benchmark (80% Horizon)080% Time Horizon (hours)4

Interactive version: theaggregate.ai/model?slug=gpt-3-5-turbo-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.