The Model Index
Up to four models

Qwen3-30B-A3B-Instruct (Jul 2025) vs DeepSeek-R1-Distill-Qwen-32B

On the index (GPT-4 = 100), Qwen3-30B-A3B-Instruct (Jul 2025) scores 127 and DeepSeek-R1-Distill-Qwen-32B 127. 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 Qwen3-30B-A3B-Instruct (Jul 2025)
Presets
Qwen3-30B-A3B-Instruct (Jul 2025)
127111–143
WeightsOpen
ReleasedJul 2025
Price in / out$0.10 / $0.30
Context262K
Core tests taken1 of 9
DeepSeek-R1-Distill-Qwen-32B
127111–142
WeightsOpen
ReleasedJan 2025
Price in / out–
Context–
Core tests taken1 of 9

Qwen3-30B-A3B-Instruct (Jul 2025) and DeepSeek-R1-Distill-Qwen-32B are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Qwen3-30B-A3B-Instruct (Jul 2025)DeepSeek-R1-Distill-Qwen-32B
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
TestQwen3-30B-A3B-Instruct (Jul 2025)DeepSeek-R1-Distill-Qwen-32B
Reasoning & knowledge
GPQA Diamond (Epoch AI)55.6%64.1%
Maths
AIME-style maths (OTIS mock)62.2%55.6%

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

This page as a chartDownload PNG