The Model Index
Up to four models

Phi-3 vs Claude 2.1

On the index (GPT-4 = 100), Phi-3 scores 97 and Claude 2.1 96. 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 Phi-3
Presets
Phi-3
9780–114
WeightsOpen
ReleasedApr 2024
Price in / out–
Context–
Core tests taken1 of 9
Claude 2.1
9678–115
WeightsClosed
ReleasedNov 2023
Price in / out–
Context–
Core tests taken1 of 9

Phi-3 and Claude 2.1 are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Phi-3Claude 2.1
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)
Every result as a table
TestPhi-3Claude 2.1
Reasoning & knowledge
GPQA Diamond (Epoch AI)27.6%33.0%
MMLU (HELM runs)77.5%73.5%

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

This page as a chartDownload PNG