Skip to content

GPT-4 (Jun 2023)

ModelActive
by OpenAI · family “gpt-jun”
Epoch Capabilities Index
123.1 #181 of 268
90% CI 116.1 – 127.0
Released
13 Jun 2023
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (13)

BenchmarkDomainScorevs best recordedSettingRunSource
LMCAagents17.1%
25%
——External ↗
DTBenchreasoning62.7%
63%
——External ↗
Mystery Game Puzzlesgames12.0% ±3.3
14%
—28 Aug 2026Epoch ↗
Chess Puzzlesgames4.0% ±2.0
6%
—7 Aug 2026Eval log ↗
METR Time Horizonsagents29.3%
34%
——External ↗
WeirdMLcoding12.4% ±0.0
13%
——External ↗
OTIS Mock AIME 2024-2025math1.1% ±0.5
1%
—23 Oct 2025Eval log ↗
GPQA diamondscience30.7% ±2.3
32%
—27 Jan 2025Eval log ↗
BBHreasoning75.1%
84%
——External ↗
GSM8Kmath90.0%
95%
——External ↗
MATH level 5math23.0% ±0.8
23%
—27 Jan 2025Epoch ↗
MMLUknowledge82.4%
94%
——External ↗
TriviaQAother84.8%
97%
——External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens
This model has no public API price listing

0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 7h ago. Steps show when the price changed.

Events