The Model Index
Up to four models

GPT-4 Turbo vs Phi-2

GPT-4 Turbo vs Phi-2, side by side on the same third-party tests. 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 Turbo
Presets
GPT-4 Turbo
10791–123
WeightsClosed
ReleasedNov 2023
Price in / out–
Context–
Core tests taken2 of 9
Phi-2
–no third-party score yet
WeightsOpen
ReleasedDec 2023
Price in / out–
Context–
Core tests taken0 of 9

Test by testthird-party results

GPT-4 TurboPhi-2
0%25%50%75%100%REASONING & KNOWLEDGEMMLU (HELM runs)MMLU (HELM runs)
Every result as a table
TestGPT-4 TurboPhi-2
Reasoning & knowledge
MMLU (HELM runs)79.6%58.4%
Task length · METR21 sec

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

This page as a chartDownload PNG