The Model Index
Up to four models

DeepSeek-R1-Distill-Qwen-32B vs GPT-4.5

On the index (GPT-4 = 100), DeepSeek-R1-Distill-Qwen-32B scores 127 and GPT-4.5 125. 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 DeepSeek-R1-Distill-Qwen-32B
Presets
DeepSeek-R1-Distill-Qwen-32B
127111–142
WeightsOpen
ReleasedJan 2025
Price in / out–
Context–
Core tests taken1 of 9
GPT-4.5
125109–141
WeightsClosed
ReleasedFeb 2025
Price in / out–
Context–
Core tests taken3 of 9

DeepSeek-R1-Distill-Qwen-32B and GPT-4.5 are too close to call (2 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

DeepSeek-R1-Distill-Qwen-32BGPT-4.5
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
TestDeepSeek-R1-Distill-Qwen-32BGPT-4.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)64.1%68.7%
Maths
AIME-style maths (OTIS mock)55.6%37.8%

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

This page as a chartDownload PNG