Skip to content
English

Switch theme

OpenAI

GPT-4 (Jun 2023) benchmark results

5 results on 5 benchmarks from 2 sources.

Closed Released: Jun 13, 2023 Updated Oct 22, 2026

Also listed as: gpt-4-0613 · GPT-4 (0613)

All benchmark results

Benchmarks Score Rank Setting Source type Date
LMArena Text 1276 305 Overall, style control on; 88723 votes; 95% CI 1272–1280“gpt-4-0613” Official leaderboard Oct 8, 2026
GPQA Diamond 30.6% 259 Epoch AI run, accuracy; effort: Jun 2023 Independent run Jan 27, 2025
MMLU 82.4% 11 Exact match; 5-shot; effort: Jun 2023 Official leaderboard via Epoch AI Jun 13, 2023
AIME (OTIS Mock AIME 2024–2025) 1.1% 255 Epoch AI run, OTIS Mock AIME 2024–2025; effort: Jun 2023 Independent run Oct 23, 2025
MATH Level 5 23.0% 83 Epoch AI run, accuracy; effort: Jun 2023 Independent run Jan 27, 2025
← AI Model Benchmarks

FAQ

Where do these GPT-4 (Jun 2023) scores come from?

From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.

Data updated: Benchmarks(UTC+8)