The Model Index
Up to four models

o4-mini vs Qwen3

On the index (GPT-4 = 100), o4-mini scores 141 and Qwen3 133. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

o4-miniQwen3
Next to o4-mini
Presets
o4-mini
141126–157
WeightsClosed
ReleasedApr 2025
Price in / out–
Context–
Core tests taken5 of 9
Qwen3
133110–156
WeightsOpen
ReleasedApr 2025
Price in / out$0.12 / $0.50
Context41K
Core tests taken0 of 9

o4-mini and Qwen3 are too close to call (9 points apart, within the uncertainty).

Test by testthird-party results

o4-miniQwen3
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMATHSMATH 500MATH 500MGSMMGSMCODINGLiveCodeBenchLiveCodeBenchPROFESSIONAL WORKLegalBenchLegalBenchTaxEval v2TaxEval v2
Every result as a table
Testo4-miniQwen3
Reasoning & knowledge
GPQA Diamond (Vals AI)74.5%70.2%
MMLU Pro80.6%81.3%
Maths
MATH 50094.2%94.6%
MGSM93.4%92.5%
Coding
LiveCodeBench82.2%70.6%
Professional work
LegalBench79.2%80.2%
TaxEval v274.8%70.7%
Task length · METR38 sec

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

This page as a chartDownload PNG