Decision model

Sieve 31B v3

1 question per request

Accuracy, all 2,198 questions
74.2%72.3% to 75.9%, 95% interval; 1,630 right
Answers kept at 99% confidence
329 of 2,1981 wrong; share right 98.3% to 99.9%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
No list priceBasis and price under Cost
Latency
1.00 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
Sieve server (sieve-serve, the maker's release code), self-hosted, BF16
Paid as
Our own hardware
Model ID
sthanika-ai/Sieve-31B-v3
Parameters
31B dense, as the maker states it (counted from the released files: 31.27B).language model (tied embeddings) + 0.58B vision encoder (not read by its server); source: counted from the checkpoint's safetensors, sthanika-ai/Sieve-31B-v3@8fcee85, huggingface.co/sthanika-ai/Sieve-31B-v3; read 10 November 2026
Hardware
1 × DGX Spark, GB10 (128 GB unified memory); BF16
Note
sthanika-ai's released Sieve-31B-v3 (sthanika-ai/Sieve-31B-v3 at 8fcee85), a full fine-tune of Gemma-4-31B-it with bidirectional attention in its global layers, read in two option orders. It ran on our hardware (one DGX Spark), one request at a time, through the server its card names (sieve-serve from the Sieve repository's main at 1e64657, on torch 2.14 where the card tested torch 2.8), text only. Probabilities rounded to 4 decimals by its own code; they sum to 1 only within that rounding. Its server reports no token counts. Its card lists English only.
Confidence from
Option score
Run
1241, 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 questions74.2%72.3% to 75.9%1,630 of 2,198
Reading91.8%89.4% to 93.6%602 of 656
Grammar66.7%64.3% to 69.0%1,028 of 1,542

Comparison group: vwxy. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading87.8%115 of 131
Sentence meaningsReading96.8%149 of 154
How a writer explains and develops ideasReading85.7%60 of 70
Topic and main point of a paragraphReading95.9%94 of 98
How a paragraph fits togetherReading84.0%89 of 106
Details that support a paragraph’s main pointReading97.9%95 of 97
Word types, such as nouns and verbsGrammar70.0%98 of 140
Groups of words built around a nounGrammar69.2%45 of 65
Verbs and their formsGrammar76.9%70 of 91
Verb forms used like nouns or modifiersGrammar84.7%61 of 72
Word endings and what they doGrammar70.9%56 of 79
How words are builtGrammar58.0%40 of 69
The roles of words and phrases in a sentenceGrammar60.7%88 of 145
How verbs show who acts and who receives the actionGrammar79.7%59 of 74
Types of sentencesGrammar72.9%62 of 85
Questions combining several grammar topicsGrammar39.5%87 of 220
Sound patterns and changesGrammar46.8%36 of 77
SpellingGrammar76.7%102 of 133
PunctuationGrammar71.8%84 of 117
Problems in sentence wordingGrammar80.0%140 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
496 of 547, first English run (1064)
Accuracy
90.7%
Non-hallucination with “I don't know”
2.2%: 1 “I don't know” of 46 not right (run 1066)
Answered with “I don't know”
99.8%: 546 of 547
Error rate with “I don't know”
8.2%: 45 of 546 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
No list price
Latency, median request, first English run
1.06 s; 1 request at once
English run
1064
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
329, of which 1 wrong (share right: 98.3% to 99.9%, 95% interval); 1,869 skipped, the model less than 99% sure
Calibration gap
2.9 points
AUROC, all questions
0.87 0.86 to 0.89
AUROC, reading
0.94 0.91 to 0.96
AUROC, grammar
0.83 0.81 to 0.85
Brier score
0.126
Accuracy of its surest answers
most confident fifth: 99.8% right; most confident half: 96.5% right; most confident four fifths: 84.5% right
Typical score of a right answer
92.4%
Typical score of a wrong answer
49.2%

Repeats

We did not repeat this setup.

Latency

Latency, median request
1.00 s (this run)
Latency, 90th percentile
1.37 s
Requests at once
1
Throughput
56.4 questions per minute of request time
Request time
39.0 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
0
Output tokens per question
0