The Model Index
Up to four models

Qwen3.5-9B vs Qwen3-235B-A22B-Instruct (Jul 2025)

On the index (GPT-4 = 100), Qwen3.5-9B scores 130 and Qwen3-235B-A22B-Instruct (Jul 2025) 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 Qwen3.5-9B
Presets
Qwen3.5-9B
130114–146
WeightsOpen
ReleasedFeb 2026
Price in / out$0.16 / $0.23
Context262K
Core tests taken1 of 9
Qwen3-235B-A22B-Instruct (Jul 2025)
130114–146
WeightsOpen
ReleasedJul 2025
Price in / out$0.14 / $0.80
Context262K
Core tests taken0 of 9

Qwen3.5-9B and Qwen3-235B-A22B-Instruct (Jul 2025) are too close to call (0 points apart, within the uncertainty), and costs 1.8× less.

Test by testthird-party results

Qwen3.5-9BQwen3-235B-A22B-Instruct (Jul 2025)
0%25%50%75%100%AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestQwen3.5-9BQwen3-235B-A22B-Instruct (Jul 2025)
Agents
DTBench71.2%78.4%
LMCA24.5%23.5%

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

This page as a chartDownload PNG