GPT-5.6 Luna Max vs GPT-6.1 Terra Max compared

GPT-6.1 Terra Max leads the intelligence index 51.3 to 23.8. Price per token, response speed and when to pick each.

Metric	GPT-5.6 Luna (Max)	GPT-6.1 Terra (Max)
Intelligence Index	23.8	51.3
Input price (per 1M tokens)	$0.20	$1.00
Output price (per 1M tokens)	$1.20	$5.00
Output speed (tokens/s)	125	114
Time to first token	108s	6.2 min
Release date	2026-07-09	2026-10-26

Metric

GPT-5.6 Luna (Max)

GPT-6.1 Terra (Max)

Intelligence Index

23.8

51.3

Input price (per 1M tokens)

$0.20

$1.00

Output price (per 1M tokens)

$1.20

$5.00

Output speed (tokens/s)

125

114

Time to first token

108s

6.2 min

Release date

2026-07-09

2026-10-26

Two OpenAI models meet here: GPT-5.6 Luna (Max) and GPT-6.1 Terra (Max). Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test. The headline gap is on the intelligence index, where GPT-6.1 Terra Max scores 51.3 and GPT-5.6 Luna Max 23.8.

The headline benchmark

The catalogue puts GPT-5.6 Luna Max at 23.8 and GPT-6.1 Terra Max at 51.3 on its intelligence index. The difference is large enough that the lower-scoring model has to win on cost or speed to stay in the running.

Across the 109 active models with an intelligence score in the catalogue, GPT-5.6 Luna Max ranks 70th and GPT-6.1 Terra Max ranks 14th.

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

Throughput and time to first token

GPT-5.6 Luna Max generates about 125 tokens per second and GPT-6.1 Terra Max about 114 tokens per second. GPT-5.6 Luna Max is ahead by 9% on throughput. Before any text appears, GPT-5.6 Luna Max takes 108 seconds and GPT-6.1 Terra Max 6.2 minutes. In an interactive app, GPT-5.6 Luna Max will feel noticeably more responsive. A first-token wait of that length suits background work better than live conversation.

Put together, an 800-token answer would take about 114 seconds from GPT-5.6 Luna Max and 6.3 minutes from GPT-6.1 Terra Max, counting the first-token wait.

Running costs

Per million tokens, GPT-5.6 Luna Max charges $0.20 for input and $1.20 for output, while GPT-6.1 Terra Max charges $1.00 and $5.00. For output tokens, GPT-6.1 Terra Max is 4.2 times the price of GPT-5.6 Luna Max.

Take 1 million input tokens and 200,000 output tokens: that comes to $0.44 on GPT-5.6 Luna Max and $2.00 on GPT-6.1 Terra Max. A bigger example, classifying 100,000 short messages at 150 input tokens and 5 output tokens each, costs $3.60 on GPT-5.6 Luna Max and $17.50 on GPT-6.1 Terra Max: a gap of $13.90.

Is the price in proportion?

Per point of intelligence index, GPT-5.6 Luna Max costs $0.019 of blended price per million tokens and GPT-6.1 Terra Max $0.039. GPT-6.1 Terra Max costs 2.1 times as much per point, which is the price of its lead.

Generation gap

The release dates are July 9, 2026 for GPT-5.6 Luna Max and October 26, 2026 for GPT-6.1 Terra Max, about 4 months apart.

Common questions about GPT-5.6 Luna Max and GPT-6.1 Terra Max

Is GPT-6.1 Terra Max better than GPT-5.6 Luna Max?

Neither wins everywhere: GPT-6.1 Terra Max scores higher on the intelligence index, 51.3 to 23.8; GPT-5.6 Luna Max is 78% cheaper on blended price; and GPT-5.6 Luna Max streams output 1.1 times as fast.

Which is cheaper, GPT-5.6 Luna Max or GPT-6.1 Terra Max?

GPT-5.6 Luna Max is cheaper on a blended basis. GPT-5.6 Luna Max lists $0.20 per million input tokens and $1.20 per million output tokens; GPT-6.1 Terra Max lists $1.00 and $5.00. For 1 million input and 200,000 output tokens that is $0.44 against $2.00.

Which model has lower latency?

GPT-5.6 Luna Max generates output faster, at 125 tokens per second against 114 tokens per second. GPT-5.6 Luna Max reaches its first token sooner (108 seconds against 6.2 minutes).

When were GPT-5.6 Luna Max and GPT-6.1 Terra Max released?

GPT-6.1 Terra Max is newer. It was released on October 26, 2026, about 4 months after GPT-5.6 Luna Max (July 9, 2026).

Where do these numbers come from?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

Final whistle

GPT-6.1 Terra Max has more going for it here, but GPT-5.6 Luna Max is not without an argument. Pick GPT-5.6 Luna Max if cost matters ($1.20 against $5.00 per million output tokens) and users are waiting on the first word. Pick GPT-6.1 Terra Max if you need the higher overall score (51.3 against 23.8) and you want the more recent release.

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the GPT-5.6 Luna (Max) and GPT-6.1 Terra (Max) pages. The AI Benchmark methodology explains how that data is collected and shown.