Decision model

Turion Jev 31B

1 question per request

Accuracy, all 2,198 questions
80.1%78.4% to 81.7%, 95% interval; 1,761 right
Answers kept at 99% confidence
42 of 2,1980 wrong; share right 91.6% to 100.0%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
No list priceBasis and price under Cost
Latency
0.405 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
Turion Jev server (turion_jev.serve on vLLM, the maker's release code), self-hosted, FP8 at load
Paid as
Our own hardware
Model ID
turion-ai/turion-jev-31b
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, turion-ai/turion-jev-31b@866c0fc, huggingface.co/turion-ai/turion-jev-31b; read 10 November 2026
Hardware
1 × DGX Spark, GB10 (128 GB unified memory); FP8 at load
Note
Turion AI's released Turion Jev 31B (turion-ai/turion-jev-31b at 866c0fc), a merged LoRA fine-tune of Gemma-4-31B-it. It ran on our hardware (one DGX Spark), one request at a time, through the server its package ships (python -m turion_jev.serve on vLLM), with the BF16 weights quantised to FP8 at load and --no-recheck (no second reading of unsure questions), both as in the card's own benchmark run, text only. Probabilities rounded to 6 decimals by its own code; they sum to 1 only within that rounding.
Confidence from
Option score
Run
1273, 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
88e48d7a1055
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions80.1%78.4% to 81.7%1,761 of 2,198
Reading92.7%90.4% to 94.4%608 of 656
Grammar74.8%72.5% to 76.9%1,153 of 1,542

Comparison group: opqr. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading90.1%118 of 131
Sentence meaningsReading96.8%149 of 154
How a writer explains and develops ideasReading87.1%61 of 70
Topic and main point of a paragraphReading96.9%95 of 98
How a paragraph fits togetherReading84.9%90 of 106
Details that support a paragraph’s main pointReading97.9%95 of 97
Word types, such as nouns and verbsGrammar82.9%116 of 140
Groups of words built around a nounGrammar75.4%49 of 65
Verbs and their formsGrammar82.4%75 of 91
Verb forms used like nouns or modifiersGrammar87.5%63 of 72
Word endings and what they doGrammar81.0%64 of 79
How words are builtGrammar52.2%36 of 69
The roles of words and phrases in a sentenceGrammar77.2%112 of 145
How verbs show who acts and who receives the actionGrammar87.8%65 of 74
Types of sentencesGrammar83.5%71 of 85
Questions combining several grammar topicsGrammar59.5%131 of 220
Sound patterns and changesGrammar50.6%39 of 77
SpellingGrammar75.9%101 of 133
PunctuationGrammar74.4%87 of 117
Problems in sentence wordingGrammar82.3%144 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 (1075)
Accuracy
90.7%
Non-hallucination with “I don't know”
8.5%: 4 “I don't know” of 47 not right (run 1077)
Answered with “I don't know”
99.3%: 543 of 547
Error rate with “I don't know”
7.9%: 43 of 543 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
No list price
Latency, median request, first English run
0.445 s; 1 request at once
English run
1075
Machine, English runs
DGX Spark
Date
13 November 2026
Request format
1 question per request
Reasoning
off
Prompt version
47f5776e71db
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

Confidence

Answers kept at 99% or more
42, of which 0 wrong (share right: 91.6% to 100.0%, 95% interval); 2,156 skipped, the model less than 99% sure
Calibration gap
11.1 points
AUROC, all questions
0.87 0.86 to 0.89
AUROC, reading
0.92 0.88 to 0.95
AUROC, grammar
0.84 0.82 to 0.86
Brier score
0.126
Accuracy of its surest answers
most confident fifth: 99.8% right; most confident half: 97.7% right; most confident four fifths: 89.8% right
Typical score of a right answer
79.6%
Typical score of a wrong answer
41.2%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.405 s (this run)
Latency, 90th percentile
0.566 s
Requests at once
1
Throughput
140.1 questions per minute of request time
Request time
15.7 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
766
Output tokens per question
0