gpt-6-astra vs qwen3-coder-30b-a3b-instruct
Pricing and scores side by side. Blank cells mean the price is undisclosed or the model did not take that test.
InputUSD / 1M tokens$10.00$0.07
OutputUSD / 1M tokens$50.00$0.28
Monthly costat 10M tokens/month$200.00₩264,781$1.23₩1,622
Context1.05M262K
Report card
Overall52.7#5/1759.6#128/175
ScienceGPQA96.1#1/15951.6#133/159
MathAA Math Indexnot taken29.0#61/94
CodingAA Coding Index76.9#4/82not taken
ReadingAA-LCR80.7#27/15532.7#128/155
KnowledgeMMLU-Pronot taken70.6#70/92
Instruction followingIFBenchnot taken32.7#110/129
Hard reasoningHLE54.7#7/1713.8#150/171
Measured and published by Artificial Analysis. Each subject is a different test, so compare within a subject rather than across them.
Try another pair
Swap one side and keep comparing.