The Model Index
Up to four models

GPT-4 vs Gemini 1.5 Flash 8B

On the index (GPT-4 = 100), GPT-4 scores 100 and Gemini 1.5 Flash 8B 99. 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-4
Presets
GPT-4
100100–100
WeightsClosed
ReleasedMar 2023
Price in / out–
Context–
Core tests taken2 of 9
Gemini 1.5 Flash 8B
9977–120
WeightsClosed
ReleasedOct 2024
Price in / out–
Context–
Core tests taken1 of 9

GPT-4 and Gemini 1.5 Flash 8B are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

GPT-4Gemini 1.5 Flash 8B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)
Every result as a table
TestGPT-4Gemini 1.5 Flash 8B
Reasoning & knowledge
GPQA Diamond (Epoch AI)35.7%33.0%
Maths
AIME-style maths (OTIS mock)0.6%4.6%
Task length · METR22 sec

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

This page as a chartDownload PNG