OpenAI: GPT-6 Luna (batch) vs Qwen: Qwen3.8 Max (0902)

For a sample job of 1 million input tokens and 250,000 output tokens, GPT-6 Luna (batch) costs $0.11 and Qwen3.8 Max (0902) costs $3.50, so GPT-6 Luna (batch) is about 31.1 times cheaper for the same work.

Both take in a similar amount of text: 1,050,000 and 1,000,000 tokens, about 1,575 and 1,500 pages.

Only Qwen3.8 Max (0902) offers video input.

On our blended benchmark score Qwen3.8 Max (0902) leads 77.3 to 63.8.

Across the 20 tasks where they differ, GPT-6 Luna (batch) scores higher on 7 (Code Completion, Code Documentation, Regex Writing and others), Qwen3.8 Max (0902) on 13 (SQL Generation, Code Review, Code Refactoring and others).

Pick GPT-6 Luna (batch) if you need lower cost; pick Qwen3.8 Max (0902) if you need video input or benchmark performance.

Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.