GPT-6.1 Terra Max vs Muse Spark 1.3 Max: which scores higher?

Comparing GPT-6.1 Terra (Max) with Muse Spark 1.3 (Max) is really a question of how much capability you are willing to give up, and what you get back for it. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed. Their widest difference is the intelligence index, with GPT-6.1 Terra Max ahead by 14.7 points (51.3 versus 36.6).

Benchmark scores

GPT-6.1 Terra Max comes out ahead on the intelligence index, 51.3 to 36.6. This is a substantial lead, not a near miss.

For context, that places GPT-6.1 Terra Max 14th and Muse Spark 1.3 Max 36th out of 109 scored models still on offer.

Specialist coding and math indexes are missing for both, so treat the overall score as the only capability signal here.

How fast they respond

Once a response is under way, GPT-6.1 Terra Max produces roughly 114 tokens per second against 140 tokens per second for Muse Spark 1.3 Max. That makes Muse Spark 1.3 Max roughly 1.2 times as fast at writing. Time to first token is 6.2 minutes for GPT-6.1 Terra Max and 36 seconds for Muse Spark 1.3 Max. Muse Spark 1.3 Max gets to its first token 10 times as fast. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

For an 800-token response, first token plus generation comes to roughly 6.3 minutes on GPT-6.1 Terra Max and 42 seconds on Muse Spark 1.3 Max.

When they came out

Muse Spark 1.3 Max came first, on September 2, 2026; GPT-6.1 Terra Max followed on October 26, 2026.

Input versus output cost

The list prices are $1.00 in and $5.00 out for GPT-6.1 Terra Max, and $1.25 in and $4.25 out for Muse Spark 1.3 Max, per million tokens. Neither is cheaper across the board: GPT-6.1 Terra Max has the lower input rate and Muse Spark 1.3 Max the lower output rate, so the shape of your traffic decides it.

Take 1 million input tokens and 200,000 output tokens: that comes to $2.00 on GPT-6.1 Terra Max and $2.10 on Muse Spark 1.3 Max. Scale it up to classifying 100,000 short messages at 150 input tokens and 5 output tokens each and the bill is $17.50 for GPT-6.1 Terra Max against $20.88 for Muse Spark 1.3 Max. On a 3:1 blend of input to output tokens, that works out to $2.00 versus $2.00 per million.

Value for money

Per point of intelligence index, GPT-6.1 Terra Max costs $0.039 of blended price per million tokens and Muse Spark 1.3 Max $0.055. With the higher score and the lower cost per point, GPT-6.1 Terra Max is the better value per point on these numbers.