The Model Index
Up to four models

Qwen2.5 vs DeepSeek-R1-Distill-Qwen-1.5B

On the index (GPT-4 = 100), Qwen2.5 scores 112 and DeepSeek-R1-Distill-Qwen-1.5B 111. 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 Qwen2.5
Presets
Qwen2.5
11296–128
WeightsOpen
ReleasedSep 2024
Price in / out$0.36 / $0.40
Context33K
Core tests taken2 of 9
DeepSeek-R1-Distill-Qwen-1.5B
11194–128
WeightsOpen
ReleasedJan 2025
Price in / out–
Context–
Core tests taken1 of 9

Qwen2.5 and DeepSeek-R1-Distill-Qwen-1.5B are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Qwen2.5DeepSeek-R1-Distill-Qwen-1.5B
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
TestQwen2.5DeepSeek-R1-Distill-Qwen-1.5B
Reasoning & knowledge
GPQA Diamond (Epoch AI)49.1%33.6%
Maths
AIME-style maths (OTIS mock)8.1%21.4%
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