The Model Index
Up to four models

Qwen3-30B-A3B-Thinking (Jul 2025) vs Qwen3.5-9B

On the index (GPT-4 = 100), Qwen3-30B-A3B-Thinking (Jul 2025) scores 131 and Qwen3.5-9B 130. 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-Thinking (Jul 2025)
Presets
Qwen3-30B-A3B-Thinking (Jul 2025)
131115–147
WeightsOpen
ReleasedJul 2025
Price in / out–
Context–
Core tests taken1 of 9
Qwen3.5-9B
130114–146
WeightsOpen
ReleasedFeb 2026
Price in / out$0.16 / $0.23
Context262K
Core tests taken1 of 9

Qwen3-30B-A3B-Thinking (Jul 2025) and Qwen3.5-9B 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-Thinking (Jul 2025)Qwen3.5-9B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestQwen3-30B-A3B-Thinking (Jul 2025)Qwen3.5-9B
Reasoning & knowledge
GPQA Diamond (Epoch AI)70.1%79.0%
Maths
AIME-style maths (OTIS mock)70.3%61.7%
Agents
DTBench69.3%71.2%
LMCA19.5%24.5%

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

This page as a chartDownload PNG