Decision model

Karpo Decision 31B

1 question per request

Accuracy, all 2,198 questions
77.8%76.0% to 79.5%, 95% interval; 1,710 right
Answers kept at 99% confidence
505 of 2,1980 wrong; share right 99.2% to 100.0%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
$0.105$105Basis and price under Cost
Latency
0.159 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
karpo-decision server (the System One server of the card's karpo-decision package, machinepulse-ai/karpo-decision at ac40d39), self-hosted, BF16
Paid as
Our own hardware
Model ID
karpo-decision
Parameters
31B dense, as the maker states it (counted from the released files: 31.27B).language model + vision encoder (575,743,536) + 255-way readout (1,370,880); the card says 31.3B in bf16 plus the readout; source: counted from the checkpoint's safetensors, MachinePulseAI/Karpo Decision 31B@d69cdd5, huggingface.co/MachinePulseAI/Karpo Decision 31B; read 15 November 2026
Hardware
1 × RTX PRO 6000 Blackwell (96 GB); BF16
Note
MachinePulse's released checkpoint, a fine-tune of Gemma-4-31B-it with a 255-way readout that also reads images, run on our hardware through the System One server of the package its card ships (karpo-decision at ac40d39). Its Reading runs shared the server with the Logic & Math site's runs from 05:00 UTC on 15 November 2026, so its latency and GPU-time cost were measured under that load.
Confidence from
Option score
Run
1156, 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
815031979442
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions77.8%76.0% to 79.5%1,710 of 2,198
Reading93.4%91.3% to 95.1%613 of 656
Grammar71.1%68.8% to 73.3%1,097 of 1,542

Comparison group: rstu. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading89.3%117 of 131
Sentence meaningsReading96.8%149 of 154
How a writer explains and develops ideasReading90.0%63 of 70
Topic and main point of a paragraphReading95.9%94 of 98
How a paragraph fits togetherReading87.7%93 of 106
Details that support a paragraph’s main pointReading100.0%97 of 97
Word types, such as nouns and verbsGrammar78.6%110 of 140
Groups of words built around a nounGrammar78.5%51 of 65
Verbs and their formsGrammar82.4%75 of 91
Verb forms used like nouns or modifiersGrammar86.1%62 of 72
Word endings and what they doGrammar69.6%55 of 79
How words are builtGrammar56.5%39 of 69
The roles of words and phrases in a sentenceGrammar69.7%101 of 145
How verbs show who acts and who receives the actionGrammar81.1%60 of 74
Types of sentencesGrammar78.8%67 of 85
Questions combining several grammar topicsGrammar50.5%111 of 220
Sound patterns and changesGrammar45.5%35 of 77
SpellingGrammar74.4%99 of 133
PunctuationGrammar74.4%87 of 117
Problems in sentence wordingGrammar82.9%145 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
504 of 547, first English run (1159)
Accuracy
92.1%
Non-hallucination with “I don't know”
0.0%: 0 “I don't know” of 42 not right (run 1161)
Answered with “I don't know”
100.0%: 547 of 547
Error rate with “I don't know”
7.7%: 42 of 547 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.145145from GPU time
Latency, median request, first English run
0.207 s; 1 request at once
English run
1159
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
505, of which 0 wrong (share right: 99.2% to 100.0%, 95% interval); 1,693 skipped, the model less than 99% sure
Calibration gap
2.3 points
AUROC, all questions
0.88 0.86 to 0.89
AUROC, reading
0.93 0.90 to 0.96
AUROC, grammar
0.84 0.82 to 0.86
Brier score
0.115
Accuracy of its surest answers
most confident fifth: 100.0% right; most confident half: 98.0% right; most confident four fifths: 87.5% right
Typical score of a right answer
95.1%
Typical score of a wrong answer
54.0%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.159 s (this run)
Latency, 90th percentile
0.207 s
Requests at once
1
Throughput
395.9 questions per minute of request time
Request time
5.6 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

Cost per 1,000 questionsper 1M questions
$0.105$105
Whole run
$0.23
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
426
Output tokens per question
0