Compare AI models

Decision facts

• Qwen3.8 Max (0902) is #32; Qwen3 Coder 480B A35B is #85 on the same current language board.
• Index scores are 66.6 for Qwen3.8 Max (0902) and 46.0 for Qwen3 Coder 480B A35B. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.
• Evidence differs: Qwen3.8 Max (0902) is Estimated; Qwen3 Coder 480B A35B is Measured.
• Listed output price per 1M tokens is $6.00 for Qwen3.8 Max (0902) and $1.00 for Qwen3 Coder 480B A35B. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $7.00 for Qwen3.8 Max (0902) versus $1.10 for Qwen3 Coder 480B A35B. Qwen3 Coder 480B A35B costs 84.3% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
• Published context is 1,000,000 tokens for Qwen3.8 Max (0902) and 262,144 for Qwen3 Coder 480B A35B.
• Weight access differs: Qwen3.8 Max (0902) is none; Qwen3 Coder 480B A35B is open.
• ModelCap currently lists 1 providers for Qwen3.8 Max (0902) and 5 for Qwen3 Coder 480B A35B.

These are separate published fields, not a synthetic winner. ModelCap does not collapse price, access, context, and capability evidence into a hidden recommendation score.