Chat model

Gemini 3.8 Flash

high reasoning · 16 questions per request

98.1% of the 2,198 questions right (97.4% to 98.6%, 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: Gemini API
Paid as: Provider service
Model ID: gemini-3.8-flash
Confidence from: Written estimate
Run: 140, 7 October 2026

Settings

Reasoning: high
Request format: 16 questions per request
Requests at once: 4
Temperature: not recorded
Harness seed: 0
Harness commit: not recorded
Prompt version: not recorded

Thinking levels (Google's thinking documentation, read 28 October 2026): low, medium (default), high. Top level: high. This run: high.

Results

Questions	Accuracy	95% interval	Right
All questions	98.1%	97.4% to 98.6%	2,156 of 2,198
Reading	97.1%	95.5% to 98.1%	637 of 656
Grammar	98.5%	97.8% to 99.0%	1,519 of 1,542

Comparison group: a. Compare with another setup.

Accuracy by topic

Topic	Part	Accuracy	Right
Word and phrase meanings	Reading	96.9%	127 of 131
Sentence meanings	Reading	99.4%	153 of 154
How a writer explains and develops ideas	Reading	94.3%	66 of 70
Topic and main point of a paragraph	Reading	98.0%	96 of 98
How a paragraph fits together	Reading	93.4%	99 of 106
Details that support a paragraph’s main point	Reading	99.0%	96 of 97
Word types, such as nouns and verbs	Grammar	98.6%	138 of 140
Groups of words built around a noun	Grammar	100.0%	65 of 65
Verbs and their forms	Grammar	100.0%	91 of 91
Verb forms used like nouns or modifiers	Grammar	98.6%	71 of 72
Word endings and what they do	Grammar	98.7%	78 of 79
How words are built	Grammar	97.1%	67 of 69
The roles of words and phrases in a sentence	Grammar	97.9%	142 of 145
How verbs show who acts and who receives the action	Grammar	98.6%	73 of 74
Types of sentences	Grammar	98.8%	84 of 85
Questions combining several grammar topics	Grammar	98.6%	217 of 220
Sound patterns and changes	Grammar	100.0%	77 of 77
Spelling	Grammar	100.0%	133 of 133
Punctuation	Grammar	98.3%	115 of 117
Problems in sentence wording	Grammar	96.0%	168 of 175

Confidence

Answers kept at 99% or more: 1,845, of which 10 wrong (share right: 99.0% to 99.7%, 95% interval); 353 skipped, the model less than 99% sure
Calibration gap: 1.1 points
AUROC, all questions: 0.83 0.75 to 0.90
AUROC, reading: 0.90 0.82 to 0.96
AUROC, grammar: 0.77 0.65 to 0.87
Brier score: 0.017
Accuracy of its surest answers: most confident fifth: 99.4% right; most confident half: 99.4% right; most confident four fifths: 99.4% right
Typical score of a right answer: 100.0%
Typical score of a wrong answer: 95.0%

Repeats

We did not repeat this setup.

Latency

Latency, median request: 53.7 s (this run)
Latency, 90th percentile: 134.2 s
Requests at once: 4
Throughput: 51.0 questions per minute of request time
Request time: 43.1 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: $2.42
Whole run: $5.32
Basis: Estimated from published prices and recorded token usage
Price: $0.75 input, $0.075 cached input, $3.75 output per 1M tokens (source, 2026-10-08)
Input tokens per question: 220
Output tokens per question: 601