The Model Index
Up to four models

GPT-4o mini vs GPT-4 (Jun 2023)

On the index (GPT-4 = 100), GPT-4o mini scores 104 and GPT-4 (Jun 2023) 102. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-4o mini
Presets
GPT-4o mini
10487–120
WeightsClosed
ReleasedJul 2024
Price in / out$0.15 / $0.60
Context128K
Core tests taken3 of 9
GPT-4 (Jun 2023)
10285–119
WeightsClosed
ReleasedJun 2023
Price in / out$30 / $60
Context8K
Core tests taken1 of 9

GPT-4o mini and GPT-4 (Jun 2023) are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, and costs 143× less.

Test by testthird-party results

GPT-4o miniGPT-4 (Jun 2023)
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)CODINGWeirdMLWeirdMLAGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzles
Every result as a table
TestGPT-4o miniGPT-4 (Jun 2023)
Reasoning & knowledge
GPQA Diamond (Epoch AI)37.7%30.6%
MMLU (HELM runs)76.7%82.4%
Maths
AIME-style maths (OTIS mock)6.9%1.1%
MATH (level 5)52.6%23.0%
Coding
WeirdML11.8%12.4%
Agents
DTBench54.4%62.7%
LMCA10.4%17.1%
Mystery game puzzles12.0%12.0%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG