Chat model

GPT-6.1 Terra

low reasoning · 16 questions per request

90.9% of the 2,198 questions right (89.6% to 92.0%, 95% interval). Back to the leaderboard.

Which decision model can go first in front of it? See the Routing tab.

How we called it

Kind: Chat model
Access: Codex CLI, ChatGPT subscription
Paid as: Subscription
Model ID: gpt-6.1-terra
Confidence from: Written estimate
Run: 274, 28 October 2026

Settings

Reasoning: low
Request format: 16 questions per request
Requests at once: 1
Temperature: not recorded
Harness seed: 0
Harness commit: 0fbd97b0899d
Prompt version: 254597b8be16

Reasoning effort levels (OpenAI's model page, read 28 October 2026): none, low, medium (default), high, xhigh, max. Top level: max. This run: low.

Results

Questions	Accuracy	95% interval	Right
All questions	90.9%	89.6% to 92.0%	1,997 of 2,198
Reading	95.9%	94.1% to 97.2%	629 of 656
Grammar	88.7%	87.0% to 90.2%	1,368 of 1,542

Comparison group: ijk. Compare with another setup.

Accuracy by topic

Topic	Part	Accuracy	Right
Word and phrase meanings	Reading	96.9%	127 of 131
Sentence meanings	Reading	97.4%	150 of 154
How a writer explains and develops ideas	Reading	91.4%	64 of 70
Topic and main point of a paragraph	Reading	95.9%	94 of 98
How a paragraph fits together	Reading	92.5%	98 of 106
Details that support a paragraph’s main point	Reading	99.0%	96 of 97
Word types, such as nouns and verbs	Grammar	93.6%	131 of 140
Groups of words built around a noun	Grammar	89.2%	58 of 65
Verbs and their forms	Grammar	95.6%	87 of 91
Verb forms used like nouns or modifiers	Grammar	95.8%	69 of 72
Word endings and what they do	Grammar	92.4%	73 of 79
How words are built	Grammar	78.3%	54 of 69
The roles of words and phrases in a sentence	Grammar	89.7%	130 of 145
How verbs show who acts and who receives the action	Grammar	90.5%	67 of 74
Types of sentences	Grammar	94.1%	80 of 85
Questions combining several grammar topics	Grammar	81.8%	180 of 220
Sound patterns and changes	Grammar	71.4%	55 of 77
Spelling	Grammar	90.2%	120 of 133
Punctuation	Grammar	83.8%	98 of 117
Problems in sentence wording	Grammar	94.9%	166 of 175

Confidence

Answers kept at 99% or more: 1,306, of which 27 wrong (share right: 97.0% to 98.6%, 95% interval); 892 skipped, the model less than 99% sure
Calibration gap: 6.0 points
AUROC, all questions: 0.82 0.79 to 0.85
AUROC, reading: 0.89 0.80 to 0.95
AUROC, grammar: 0.80 0.77 to 0.83
Brier score: 0.079
Accuracy of its surest answers: most confident fifth: 98.3% right; most confident half: 98.0% right; most confident four fifths: 95.9% right
Typical score of a right answer: 99.0%
Typical score of a wrong answer: 94.0%

Repeats

Run 5 times on a sample of 200 questions.

Answers changed in 5 runs: 14 of 200
Same wrong answer in all 5: 4 of 200
Wrong in at least one run: 18 of 200
Accuracy in each run: 93.0%, 96.0%, 96.0%, 95.5%, 96.0%

Latency

Latency, median request: 4.24 s (this run)
Latency, 90th percentile: 5.36 s
Requests at once: 1
Throughput: 206.8 questions per minute of request time
Request time: 10.6 minutes, over the requests whose answers were kept

Latency: the time from sending one request to receiving its answer, measured from our computer, network and any retries within the request included. Request time: the time at least one request was in flight, over the requests whose answers were kept. It is not the run's elapsed time: it leaves out requests that failed and any pause before a run was resumed.

Cost

$ per 1,000 questions: $0.43
Whole run: $0.94
Basis: Subscription run priced as if we had used the API
Price: $1 input, $0.05 cached input, $1.25 cache writes, $5 output per 1M tokens (source, 2026-10-28)
Input tokens per question: 529
Output tokens per question: 14