The Model Index
Up to four models

Grok 4 vs Qwen3-235B-A22B-Thinking (Jul 2025)

On the index (GPT-4 = 100), Grok 4 scores 148 and Qwen3-235B-A22B-Thinking (Jul 2025) 138. 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 Grok 4
Presets
Grok 4
148132–164
WeightsClosed
ReleasedJul 2025
Price in / out–
Context–
Core tests taken2 of 9
Qwen3-235B-A22B-Thinking (Jul 2025)
138121–154
WeightsOpen
ReleasedJul 2025
Price in / out$0.45 / $3.5
Context128K
Core tests taken1 of 9

Grok 4 leads Qwen3-235B-A22B-Thinking (Jul 2025) by 10 points.

Test by testthird-party results

Grok 4Qwen3-235B-A22B-Thinking (Jul 2025)
0%25%50%75%100%REASONING & KNOWLEDGEFiction.LiveBenchFiction.LiveBenchMATHSFrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGWeirdMLWeirdML
Every result as a table
TestGrok 4Qwen3-235B-A22B-Thinking (Jul 2025)
Reasoning & knowledge
Fiction.LiveBench94.4%75.0%
Maths
FrontierMath (2025 set)19.7%8.5%
FrontierMath tier 4 (2025 set)2.1%0.0%
Coding
WeirdML45.7%41.0%
Task length · METR40 sec

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

This page as a chartDownload PNG