Decision model

Chinese Decision Pointer 4B

1 question per request

Accuracy, all 2,198 questions
46.7%44.6% to 48.8%, 95% interval; 1,026 right
Answers kept at 99% confidence
51 of 2,1981 wrong; share right 89.7% to 99.7%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
$0.025$24.58Basis and price under Cost
Latency
0.035 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
Decision Index engine (compactor's di_serve.py around the engine its card ships), self-hosted, BF16
Paid as
Our own hardware
Model ID
Chinese-Decision-Pointer-4B
Parameters
4B dense, as the maker states it (counted from the released files: 4.21B).language model with its pointer readout, text only; source: counted from the checkpoint's safetensors, quincyqiang/chinese-decision-pointer-4b@889f23e, huggingface.co/quincyqiang/chinese-decision-pointer-4b; read 15 November 2026
Hardware
1 × RTX PRO 6000 Blackwell (96 GB); BF16
Note
quincyqiang's released Chinese Decision Pointer 4B (quincyqiang/chinese-decision-pointer-4b at 889f23e), a merged LoRA fine-tune of Qwen3.5-4B that reads every candidate's probability in one forward pass. Its card ships only a Decision Index engine (ChineseDecisionEngine from yanqiangmiffy/chinese-decision at c16450b), so it ran on our hardware behind compactor's di_serve.py, with the card's debias 'reverse' (the original and reversed option order averaged), without causal-conv1d (PyTorch's reference convolution), text only.
Confidence from
Option score
Run
1206, 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
7bc1f66c76b0
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions46.7%44.6% to 48.8%1,026 of 2,198
Reading70.9%67.3% to 74.2%465 of 656
Grammar36.4%34.0% to 38.8%561 of 1,542

Comparison group: ηθ. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading57.3%75 of 131
Sentence meaningsReading76.6%118 of 154
How a writer explains and develops ideasReading67.1%47 of 70
Topic and main point of a paragraphReading87.8%86 of 98
How a paragraph fits togetherReading62.3%66 of 106
Details that support a paragraph’s main pointReading75.3%73 of 97
Word types, such as nouns and verbsGrammar36.4%51 of 140
Groups of words built around a nounGrammar44.6%29 of 65
Verbs and their formsGrammar38.5%35 of 91
Verb forms used like nouns or modifiersGrammar37.5%27 of 72
Word endings and what they doGrammar40.5%32 of 79
How words are builtGrammar44.9%31 of 69
The roles of words and phrases in a sentenceGrammar31.0%45 of 145
How verbs show who acts and who receives the actionGrammar32.4%24 of 74
Types of sentencesGrammar32.9%28 of 85
Questions combining several grammar topicsGrammar24.5%54 of 220
Sound patterns and changesGrammar36.4%28 of 77
SpellingGrammar29.3%39 of 133
PunctuationGrammar36.8%43 of 117
Problems in sentence wordingGrammar54.3%95 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
440 of 547, first English run (1209)
Accuracy
80.4%
Non-hallucination with “I don't know”
3.7%: 4 “I don't know” of 108 not right (run 1211)
Answered with “I don't know”
99.3%: 543 of 547
Error rate with “I don't know”
19.2%: 104 of 543 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.02727.21from GPU time
Latency, median request, first English run
0.038 s; 1 request at once
English run
1209
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
51, of which 1 wrong (share right: 89.7% to 99.7%, 95% interval); 2,147 skipped, the model less than 99% sure
Calibration gap
11.7 points
AUROC, all questions
0.73 0.71 to 0.75
AUROC, reading
0.81 0.78 to 0.85
AUROC, grammar
0.63 0.60 to 0.66
Brier score
0.220
Accuracy of its surest answers
most confident fifth: 83.4% right; most confident half: 62.2% right; most confident four fifths: 52.1% right
Typical score of a right answer
68.1%
Typical score of a wrong answer
46.2%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.035 s (this run)
Latency, 90th percentile
0.043 s
Requests at once
1
Throughput
1688.4 questions per minute of request time
Request time
1.3 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
$0.025$24.58
Whole run
$0.054
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
728
Output tokens per question
0