Decision model

Verdin-4B-v1.1

1 question per request

Accuracy, all 2,198 questions
46.8%44.7% to 48.9%, 95% interval; 1,028 right
Answers kept at 99% confidence
27 of 2,1980 wrong; share right 87.5% to 100.0%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
$0.034$34.21Basis and price under Cost
Latency
0.049 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
Verdin server (the card's own python -m verdin.server, in the package versions its card lists), self-hosted, BF16
Paid as
Our own hardware
Model ID
Verdin-4B-v1.1
Parameters
4B dense, as the maker states it (counted from the released files: 4.21B).language model with the merged LoRA and its pointer head; its card says 4.21B served; source: counted from the checkpoint's safetensors, victorbennett/Verdin-4B-v1.1@45830d2, huggingface.co/victorbennett/Verdin-4B-v1.1; read 15 November 2026
Hardware
1 × RTX PRO 6000 Blackwell (96 GB); BF16
Note
victorbennett's released Verdin-4B-v1.1 (victorbennett/Verdin-4B-v1.1 at 45830d2): Qwen3.5-4B with a LoRA fine-tune merged into its weights (the mean of three seeds' LoRA runs) and a pointer head that reads the option-boundary tokens, 4.21B parameters served. It ran on our hardware through its card's own server, without causal-conv1d (its torch convolution path), text only. Weights CC-BY-NC-4.0 (research use).
Confidence from
Option score
Run
1244, 15 November 2026

Settings

Reasoning
off
Request format
1 question per request
Requests at once
1
Temperature
not recorded
Run record: harness seed, harness commit and prompt version
Harness seed
0
Harness commit
28d1c0e8e51a
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions46.8%44.7% to 48.9%1,028 of 2,198
Reading71.2%67.6% to 74.5%467 of 656
Grammar36.4%34.0% to 38.8%561 of 1,542

Comparison group: θ. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading52.7%69 of 131
Sentence meaningsReading81.2%125 of 154
How a writer explains and develops ideasReading64.3%45 of 70
Topic and main point of a paragraphReading87.8%86 of 98
How a paragraph fits togetherReading63.2%67 of 106
Details that support a paragraph’s main pointReading77.3%75 of 97
Word types, such as nouns and verbsGrammar40.0%56 of 140
Groups of words built around a nounGrammar44.6%29 of 65
Verbs and their formsGrammar34.1%31 of 91
Verb forms used like nouns or modifiersGrammar43.1%31 of 72
Word endings and what they doGrammar38.0%30 of 79
How words are builtGrammar27.5%19 of 69
The roles of words and phrases in a sentenceGrammar35.9%52 of 145
How verbs show who acts and who receives the actionGrammar36.5%27 of 74
Types of sentencesGrammar34.1%29 of 85
Questions combining several grammar topicsGrammar30.5%67 of 220
Sound patterns and changesGrammar16.9%13 of 77
SpellingGrammar31.6%42 of 133
PunctuationGrammar36.8%43 of 117
Problems in sentence wordingGrammar52.6%92 of 175

English

The Text tab's 547 kept reading questions translated into English, asked with this setup's Text tab settings. Every setup: English reading; against Turkish: English and Turkish.

Right answers
450 of 547, first English run (1247)
Accuracy
82.3%
Non-hallucination with “I don't know”
2.1%: 2 “I don't know” of 96 not right (run 1249)
Answered with “I don't know”
99.6%: 545 of 547
Error rate with “I don't know”
17.2%: 94 of 545 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.03434.28from GPU time
Latency, median request, first English run
0.052 s; 1 request at once
English run
1247
Machine, English runs
RTX PRO 6000
Date
15 November 2026
Request format
1 question per request
Reasoning
off
Prompt version
47f5776e71db
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

Confidence

Answers kept at 99% or more
27, of which 0 wrong (share right: 87.5% to 100.0%, 95% interval); 2,171 skipped, the model less than 99% sure
Calibration gap
9.8 points
AUROC, all questions
0.75 0.73 to 0.77
AUROC, reading
0.83 0.80 to 0.86
AUROC, grammar
0.66 0.63 to 0.69
Brier score
0.207
Accuracy of its surest answers
most confident fifth: 86.0% right; most confident half: 65.6% right; most confident four fifths: 52.5% right
Typical score of a right answer
71.4%
Typical score of a wrong answer
40.8%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.049 s (this run)
Latency, 90th percentile
0.056 s
Requests at once
1
Throughput
1213.0 questions per minute of request time
Request time
1.8 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

Cost per 1,000 questionsper 1M questions
$0.034$34.21
Whole run
$0.075
Basis
Estimated from GPU time: the run's request time x the GPUs its server held x Runpod's on-demand price for an RTX PRO 6000, $2.49 per GPU-hour (read 5 November 2026). A cloud-equivalent estimate, not measured spending.
Price
$2.49 per GPU-hour, 1 GPU, for the run's request time (source, 2026-11-05)
Input tokens per question
436
Output tokens per question
0