GPT-6 Sol Max vs Kimi K3.1 Pro: speed and benchmark comparison

If you only looked at the intelligence index, GPT-6 Sol (Max) and Kimi K3.1 Pro would be hard to tell apart. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed. GPT-6 Sol Max streams output at about 127 tokens per second, 4.7 times the rate of Kimi K3.1 Pro.

GPT-6 Sol Max is the faster writer

Measured output speed is 127 tokens per second for GPT-6 Sol Max and 27 tokens per second for Kimi K3.1 Pro. That makes GPT-6 Sol Max roughly 4.7 times as fast at writing. Time to first token is 91 seconds for GPT-6 Sol Max and 3.0 seconds for Kimi K3.1 Pro. Short replies favour Kimi K3.1 Pro; beyond about 3,000 tokens, GPT-6 Sol Max claws the time back. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

For a 2,000-token response, first token plus generation comes to roughly 107 seconds on GPT-6 Sol Max and 77 seconds on Kimi K3.1 Pro.

Release timing

The release dates are September 22, 2026 for GPT-6 Sol Max and October 23, 2026 for Kimi K3.1 Pro, 31 days apart. They are effectively contemporaries.

Kimi K3.1 Pro leads on the intelligence index

The catalogue puts GPT-6 Sol Max at 44.2 and Kimi K3.1 Pro at 46.5 on its intelligence index. It is a small margin for an index that averages many evaluations.

For context, that places GPT-6 Sol Max 26th and Kimi K3.1 Pro 23rd out of 109 scored models still on offer.

For coding or maths work specifically, the catalogue has no dedicated index on either side yet.

What they cost

The list prices are $2.00 in and $10.00 out for GPT-6 Sol Max, and $2.00 in and $10.00 out for Kimi K3.1 Pro, per million tokens. The rates are identical, so price will not separate them.

Cost per point of intelligence

Dividing the blended price by the intelligence index gives a rough cost per point: $0.090 for GPT-6 Sol Max and $0.086 for Kimi K3.1 Pro, per million tokens. On that measure they are priced in proportion to their scores.