Decision model

Dexy-Decision-9B-V2

1 question per request

Accuracy, all 2,198 questions
51.6%49.5% to 53.7%, 95% interval; 1,134 right
Answers kept at 99% confidence
138 of 2,1981 wrong; share right 96.0% to 99.9%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
$0.023$23.03Basis and price under Cost
Latency
0.031 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
Dexy server (the card's Transformers d3_server.py, in its requirements.txt pins: torch 2.14.0, transformers 5.19.0), self-hosted, BF16
Paid as
Our own hardware
Model ID
Dexy-Decision-9B-V2
Parameters
9B dense, as the maker states it (counted from the released files: 8.39B).the whole checkpoint with its 0.456B vision encoder (text only here); its card says 8.394B; source: counted from the checkpoint's safetensors, Patrick-18/Dexy-Decision-9B-V2@4f434e2, huggingface.co/Patrick-18/Dexy-Decision-9B-V2; read 15 November 2026
Hardware
1 × RTX PRO 6000 Blackwell (96 GB); BF16
Note
Patrick-18's released Dexy-Decision-9B-V2 (Patrick-18/Dexy-Decision-9B-V2 at 4f434e2), a fine-tune of vLLM-SR's d3-flash (8.394B parameters with its 0.456B vision encoder, as its card says). It ran on our hardware through its card's own server, text only.
Confidence from
Option score
Run
1255, 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
c6e3cdddbbc0
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions51.6%49.5% to 53.7%1,134 of 2,198
Reading79.6%76.3% to 82.5%522 of 656
Grammar39.7%37.3% to 42.2%612 of 1,542

Comparison group: αβγδζ. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading71.0%93 of 131
Sentence meaningsReading86.4%133 of 154
How a writer explains and develops ideasReading68.6%48 of 70
Topic and main point of a paragraphReading91.8%90 of 98
How a paragraph fits togetherReading74.5%79 of 106
Details that support a paragraph’s main pointReading81.4%79 of 97
Word types, such as nouns and verbsGrammar50.7%71 of 140
Groups of words built around a nounGrammar41.5%27 of 65
Verbs and their formsGrammar46.2%42 of 91
Verb forms used like nouns or modifiersGrammar43.1%31 of 72
Word endings and what they doGrammar43.0%34 of 79
How words are builtGrammar30.4%21 of 69
The roles of words and phrases in a sentenceGrammar38.6%56 of 145
How verbs show who acts and who receives the actionGrammar47.3%35 of 74
Types of sentencesGrammar37.6%32 of 85
Questions combining several grammar topicsGrammar25.5%56 of 220
Sound patterns and changesGrammar28.6%22 of 77
SpellingGrammar38.3%51 of 133
PunctuationGrammar38.5%45 of 117
Problems in sentence wordingGrammar50.9%89 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
457 of 547, first English run (1258)
Accuracy
83.5%
Non-hallucination with “I don't know”
1.1%: 1 “I don't know” of 91 not right (run 1260)
Answered with “I don't know”
99.8%: 546 of 547
Error rate with “I don't know”
16.5%: 90 of 546 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.02525.41from GPU time
Latency, median request, first English run
0.036 s; 1 request at once
English run
1258
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
138, of which 1 wrong (share right: 96.0% to 99.9%, 95% interval); 2,060 skipped, the model less than 99% sure
Calibration gap
9.1 points
AUROC, all questions
0.77 0.75 to 0.79
AUROC, reading
0.83 0.80 to 0.87
AUROC, grammar
0.67 0.64 to 0.70
Brier score
0.199
Accuracy of its surest answers
most confident fifth: 93.2% right; most confident half: 71.4% right; most confident four fifths: 57.6% right
Typical score of a right answer
76.0%
Typical score of a wrong answer
44.7%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.031 s (this run)
Latency, 90th percentile
0.040 s
Requests at once
1
Throughput
1802.4 questions per minute of request time
Request time
1.2 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
$0.023$23.03
Whole run
$0.051
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
393
Output tokens per question
0