GPT-6 Sol versus Qwen3.8 Max 0902

The match-up at a glance

This comparison pits two frontier models, the ones you pick when quality comes first against each other: GPT-6 Sol and Qwen3.8 Max 0902, one from OpenAI, the other from Alibaba Cloud (Qwen). The first dates from September 22, 2026, the second from September 2, 2026.

All figures below come from public sources checked on October 22, 2026: models.dev and OpenRouter for prices and capabilities, Epoch AI for scores.

What the benchmarks say

On our capability index, GPT-6 Sol scores 89.2 out of 100 and Qwen3.8 Max 0902 88.4. The gap is too small to separate them.

On the 3 benchmarks reported for both, GPT-6 Sol wins 2 times and Qwen3.8 Max 0902 0:

• GPQA Diamond (PhD-level science questions): GPT-6 Sol 94.3%, Qwen3.8 Max 0902 92.3%
• OTIS Mock AIME (competition mathematics problems): GPT-6 Sol 100%, Qwen3.8 Max 0902 100%
• FrontierMath (very hard research-level mathematics): GPT-6 Sol 89.8%, Qwen3.8 Max 0902 65.6%

Pricing

GPT-6 Sol costs $2 per million input tokens and $10 per million output tokens; Qwen3.8 Max 0902 costs $2 and $6.

For a typical agent task (read 20,000 tokens, write 2,000), expect $0.06 with GPT-6 Sol versus $0.052 with Qwen3.8 Max 0902. Qwen3.8 Max 0902 is 1.2 times cheaper, a gap that adds up quickly over 1,000 tasks: $8 difference.

Run the numbers with your own volumes in the agent cost calculator.

Under the hood

GPT-6 Sol reads more in one go: 1,050,000 tokens of context (roughly 1,575 pages), versus 1,000,000 for Qwen3.8 Max 0902.

Reasoning mode: GPT-6 Sol yes, Qwen3.8 Max 0902 yes. Tool calling: GPT-6 Sol yes, Qwen3.8 Max 0902 yes. Image input: GPT-6 Sol yes, Qwen3.8 Max 0902 yes.

Neither publishes its weights: both are used through an API.

In short

Our reading of the data:

• Choose Qwen3.8 Max 0902 for a lower cost.

This verdict relies on public figures; it does not replace a trial on your own tasks.