Decision model

KnowLine-2B-Gen1

1 question per request

Accuracy, all 2,198 questions
36.8%34.8% to 38.8%, 95% interval; 809 right
Answers kept at 99% confidence
No answers at this thresholdnone of the 2,198 questions at 99% or more
Cost, $ per 1,000 questionsper 1M questions
No list priceBasis and price under Cost
Latency
0.062 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
KnowLine server (knowline_server.py over SGLang 0.5.21, PelaAI's release code), self-hosted, BF16
Paid as
Our own hardware
Model ID
PelaAI/KnowLine-2B-Gen1
Parameters
2B dense, as the maker states it (counted from the released files: 2.27B).language model (tied embeddings) + multi-token prediction layer + 0.33B vision encoder; source: counted from the checkpoint's safetensors, PelaAI/KnowLine-2B-Gen1@53245d4, huggingface.co/PelaAI/KnowLine-2B-Gen1; read 11 November 2026
Hardware
1 × DGX Spark, GB10 (128 GB unified memory); BF16
Note
PelaAI's released KnowLine-2B-Gen1 (PelaAI/KnowLine-2B-Gen1 at 53245d4), a merged LoRA fine-tune of Qwen3.5-2B with its readout temperature (T = 1.32) folded into the weights. It ran on our hardware (one DGX Spark), one request at a time, through the card's serve_knowline.sh (SGLang 0.5.21 in BF16 and the repository's knowline_server.py, which reads a request of up to 3,000 tokens twice), with vision on: its vision tower is the base model's, not trained on images. Its card lists English and Chinese.
Confidence from
Option score
Run
1079, 13 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
39a6b9a3f536
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions36.8%34.8% to 38.8%809 of 2,198
Reading54.3%50.4% to 58.0%356 of 656
Grammar29.4%27.2% to 31.7%453 of 1,542

Comparison group: μξ. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading40.5%53 of 131
Sentence meaningsReading61.7%95 of 154
How a writer explains and develops ideasReading47.1%33 of 70
Topic and main point of a paragraphReading72.4%71 of 98
How a paragraph fits togetherReading40.6%43 of 106
Details that support a paragraph’s main pointReading62.9%61 of 97
Word types, such as nouns and verbsGrammar29.3%41 of 140
Groups of words built around a nounGrammar29.2%19 of 65
Verbs and their formsGrammar36.3%33 of 91
Verb forms used like nouns or modifiersGrammar33.3%24 of 72
Word endings and what they doGrammar30.4%24 of 79
How words are builtGrammar20.3%14 of 69
The roles of words and phrases in a sentenceGrammar28.3%41 of 145
How verbs show who acts and who receives the actionGrammar31.1%23 of 74
Types of sentencesGrammar27.1%23 of 85
Questions combining several grammar topicsGrammar24.5%54 of 220
Sound patterns and changesGrammar22.1%17 of 77
SpellingGrammar28.6%38 of 133
PunctuationGrammar36.8%43 of 117
Problems in sentence wordingGrammar33.7%59 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
390 of 547, first English run (1057)
Accuracy
71.3%
Non-hallucination with “I don't know”
22.0%: 38 “I don't know” of 173 not right (run 1059)
Answered with “I don't know”
93.1%: 509 of 547
Error rate with “I don't know”
26.5%: 135 of 509 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
No list price
Latency, median request, first English run
0.062 s; 1 request at once
English run
1057
Machine, English runs
DGX Spark
Date
12 November 2026
Request format
1 question per request
Reasoning
off
Prompt version
47f5776e71db
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

Confidence

Answers kept at 99% or more
No answers at this threshold; 2,198 skipped, the model less than 99% sure
Calibration gap
8.4 points
AUROC, all questions
0.66 0.64 to 0.68
AUROC, reading
0.73 0.69 to 0.77
AUROC, grammar
0.58 0.55 to 0.61
Brier score
0.221
Accuracy of its surest answers
most confident fifth: 60.9% right; most confident half: 46.2% right; most confident four fifths: 40.7% right
Typical score of a right answer
47.9%
Typical score of a wrong answer
36.8%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.062 s (this run)
Latency, 90th percentile
0.085 s
Requests at once
1
Throughput
914.2 questions per minute of request time
Request time
2.4 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
No list price
Basis
No dollar estimate; see hardware and time
Input tokens per question
768
Output tokens per question
1