Is GPT-5.6 Terra better than GPT-6.1 Sol?

On accuracy they are statistically tied: GPT-5.6 Terra scored 75.0% and GPT-6.1 Sol 76.2% on the same 80 questions from open datasets. Similar accuracy; GPT-6.1 Sol costs less per question.

Which is cheaper, GPT-5.6 Terra or GPT-6.1 Sol?

GPT-6.1 Sol is cheaper: $0.0029 per question as billed, against $0.0063. List prices: GPT-5.6 Terra $2 in / $12 out, GPT-6.1 Sol $2 in / $10 out per million tokens.

Which is faster, GPT-5.6 Terra or GPT-6.1 Sol?

GPT-5.6 Terra is faster at 101 output tokens per second, against 41. Time to first token: 1.1 s for GPT-5.6 Terra, 2.1 s for GPT-6.1 Sol.

Which has the larger context window, GPT-5.6 Terra or GPT-6.1 Sol?

Both accept about the same amount of context: 1.1M and 1.1M tokens.

Head to head · tested 27 Oct 2026

GPT-5.6 Terra vs GPT-6.1 Sol: accuracy, speed and price

Similar accuracy; GPT-6.1 Sol costs less per question.

OpenAIGPT-5.6 Terra75.0% score · #15$0.0063 per question101 tok/s

OpenAIGPT-6.1 Sol76.2% score · #12$0.0029 per question41 tok/s

Verdict

Built from the measurements below

Accuracy is too close to call: GPT-5.6 Terra scored 75.0% and GPT-6.1 Sol 76.2% on the same 80 questions, a gap within what chance alone could produce.
GPT-6.1 Sol is 2.2× cheaper per question as billed ($0.0029 vs $0.0063), reasoning tokens included.
GPT-5.6 Terra generates text 2.4× faster: 101 tokens per second against 41.
GPT-5.6 Terra starts answering sooner: 1.1 s to the first token, against 2.1 s for GPT-6.1 Sol.

Which should you choose?

Choose GPT-5.6 Terra for faster streaming and a quicker first token. Choose GPT-6.1 Sol for the lower cost per correct answer ($0.0037 against $0.0084) and shorter outputs (about 224 tokens per question against 472).

Accuracy gap -1.2 points (z = -0.18). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

Measure	GPT-5.6 Terra	GPT-6.1 Sol	Edge
Verification scoreHigher is better	75.0%	76.2%	Too close to call
Cost per questionLower is better	$0.0063	$0.0029	GPT-6.1 Sol
Output speedHigher is better	101	41	GPT-5.6 Terra
Time to first tokenLower is better	1.1 s	2.1 s	GPT-5.6 Terra
End-to-end response timeLower is better	5.3 s	10.8 s	GPT-5.6 Terra
Tokens per questionLower is better	472	224	GPT-6.1 Sol
Context windowHigher is better	1.1M	1.1M	Similar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

GPT-5.6 Terra first, GPT-6.1 Sol second

Verification scorehigher is better

GPT-5.6 Terra75.0%

GPT-6.1 Sol76.2%

Cost per questionlower is better

GPT-5.6 Terra$0.0063

GPT-6.1 Sol$0.0029

Output speedhigher is better

GPT-5.6 Terra101

GPT-6.1 Sol41

Time to first tokenlower is better

GPT-5.6 Terra1.1 s

GPT-6.1 Sol2.1 s

End-to-end response timelower is better

GPT-5.6 Terra5.3 s

GPT-6.1 Sol10.8 s

Tokens per questionlower is better

GPT-5.6 Terra472

GPT-6.1 Sol224

Context windowhigher is better

GPT-5.6 Terra1.1M

GPT-6.1 Sol1.1M

Score vs. cost per question

Both models in color, every other model in grey

Results by subject and dataset

Questions answered correctly. Small samples: a gap of one or two questions is noise.

Subject	Questions	GPT-5.6 Terra	GPT-6.1 Sol
Science	30	26/30	27/30
Engineering	15	11/15	10/15
Medicine	11	4/11	5/11
Economics	9	7/9	8/9
Law	6	4/6	3/6
Humanities & social science	9	8/9	8/9
SuperGPQA dataset	50	33/50	35/50
MMLU-Pro dataset	30	27/30	26/30

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

Specification	GPT-5.6 Terra	GPT-6.1 Sol
Creator	OpenAI	OpenAI
Released	9 Jul 2026	29 Sept 2026
Weights	—	—
Reasoning	Yes	Yes
Input	file, image, text	file, image, text
Output	text	text
Context window	1.1M tokens	1.1M tokens
Knowledge cutoff	16 Feb 2026	—
List price in / out per 1M	$2 / $12	$2 / $10
Blended price per 1M (3:1)	$4.50	$4.00
Cheapest host	OpenAI · $1 / $6	OpenAI · $1 / $5
Hosts on OpenRouter	3	3
Last tested	27 Oct 2026	25 Oct 2026

Compare any two models →

GPT-5.6 Terra vs GPT-6.1 Sol: frequently asked questions

Is GPT-5.6 Terra better than GPT-6.1 Sol?: On accuracy they are statistically tied: GPT-5.6 Terra scored 75.0% and GPT-6.1 Sol 76.2% on the same 80 questions from open datasets. Similar accuracy; GPT-6.1 Sol costs less per question.
Which is cheaper, GPT-5.6 Terra or GPT-6.1 Sol?: GPT-6.1 Sol is cheaper: $0.0029 per question as billed, against $0.0063. List prices: GPT-5.6 Terra $2 in / $12 out, GPT-6.1 Sol $2 in / $10 out per million tokens.
Which is faster, GPT-5.6 Terra or GPT-6.1 Sol?: GPT-5.6 Terra is faster at 101 output tokens per second, against 41. Time to first token: 1.1 s for GPT-5.6 Terra, 2.1 s for GPT-6.1 Sol.
Which has the larger context window, GPT-5.6 Terra or GPT-6.1 Sol?: Both accept about the same amount of context: 1.1M and 1.1M tokens.