GPT-5 Chat — benchmark results

OpenAI's non-reasoning, ChatGPT-tuned GPT-5 snapshot exposed in the API as gpt-5-chat. Provider: OpenAI. Released 2025-08-07. Access: API.

Unified ELO 1697 ± 39, rank #272 of 1776 rated models, from 58 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AmongAIs750Score (50×Impostor + 10×Crewmate wins)100
AI Chess Leaderboard (Continuation)1465Elo95.5
UGI - Writing62.69Writing Score94.8
LLM Arena RU1129Arena Elo93.4
UGI - Natural Intelligence57.12NatInt Score93.4
BenchTable71.4Total Score (%)88.1
SLR-Bench - Basic100Accuracy (%)86.4
MMTU - KB mapping54.27Accuracy (%)84
MMTU - NL-2-code70.42Accuracy (%)84
SLR-Bench - Hard14Accuracy (%)80.9
MMTU - Data Cleaning45.64Accuracy (%)80
AA MMLU-Pro82.04Accuracy (%)78.5

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