Chat model

Qwen3.5-4B reasoning off · chat

reasoning off · 1 question per request

Accuracy, all 2,198 questions
46.2%44.1% to 48.3%, 95% interval; 1,015 right
Answers kept at 99% confidence
Not measureda plain answer line, no confidence
Cost, $ per 1,000 questionsper 1M questions
$0.894$894Basis and price under Cost
Latency
32.2 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Chat model
Access
our GPU (logic's server, vLLM v0.30.0 BF16, revision Qwen/Qwen3.5-4B@851bf6e), one question per request, plain answer line CEVAP: X (no answer schema); sampling min_p 0.0, presence_penalty 1.5, repetition_penalty 1.0, seed 0, temperature 1.0, top_k 20, top_p 0.95, thinking off; output cap 32,768
Paid as
Our own hardware
Model ID
qwen3.5-4b-nothink
Parameters
4B dense, as the maker states it (counted from the released files: 4.66B).language model (tied embeddings) + multi-token prediction layer + 0.33B vision encoder; source: counted from the checkpoint's safetensors, Qwen/Qwen3.5-4B@851bf6e, huggingface.co/Qwen/Qwen3.5-4B; read 9 November 2026
Hardware
1 × RTX PRO 6000 Blackwell (96 GB); BF16
Confidence from
Not measureda plain answer line, no confidence
Run
1146, 14 November 2026

Settings

Reasoning
off
Request format
1 question per request
Requests at once
32
Temperature
not recorded
Run record: harness seed, harness commit and prompt version
Harness seed
0
Harness commit
c47b12d3647b
Prompt version
ba455bb00e5c

Results

QuestionsAccuracy95% intervalRight
All questions46.2%44.1% to 48.3%1,015 of 2,198
Reading68.4%64.8% to 71.9%449 of 656
Grammar36.7%34.3% to 39.1%566 of 1,542

Comparison group: θ. Compare with another setup.

Invalid answers: 21; read from broken replies: 0; empty replies asked again: 0. Still invalid: 12 cut off at the output limit, 9 unreadable. An empty reply is asked once more; in a broken reply, any letter that is clearly readable is scored and the rest count as wrong. Invalid answers count as wrong (how).

With “Bilmiyorum” (run 1147): Invalid answers: 18; read from broken replies: 0; empty replies asked again: 0. Still invalid: 8 cut off at the output limit, 10 unreadable. (how)

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading56.5%74 of 131
Sentence meaningsReading75.3%116 of 154
How a writer explains and develops ideasReading58.6%41 of 70
Topic and main point of a paragraphReading82.7%81 of 98
How a paragraph fits togetherReading55.7%59 of 106
Details that support a paragraph’s main pointReading80.4%78 of 97
Word types, such as nouns and verbsGrammar42.9%60 of 140
Groups of words built around a nounGrammar33.8%22 of 65
Verbs and their formsGrammar39.6%36 of 91
Verb forms used like nouns or modifiersGrammar47.2%34 of 72
Word endings and what they doGrammar32.9%26 of 79
How words are builtGrammar39.1%27 of 69
The roles of words and phrases in a sentenceGrammar26.2%38 of 145
How verbs show who acts and who receives the actionGrammar44.6%33 of 74
Types of sentencesGrammar38.8%33 of 85
Questions combining several grammar topicsGrammar31.4%69 of 220
Sound patterns and changesGrammar27.3%21 of 77
SpellingGrammar33.8%45 of 133
PunctuationGrammar31.6%37 of 117
Problems in sentence wordingGrammar48.6%85 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 (1143)
Accuracy
80.4%
Non-hallucination with “I don't know”
3.6%: 4 “I don't know” of 110 not right (run 1144)
Answered with “I don't know”
99.3%: 543 of 547
Error rate with “I don't know”
19.5%: 106 of 543 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.309309from GPU time
Latency, median request, first English run
9.74 s; 32 requests at once
English run
1143
Machine, English runs
RTX PRO 6000
Date
14 November 2026
Request format
1 question per request
Reasoning
off
Prompt version
ad6f4cc346df
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

Confidence

Not measured: this setup was asked for a plain answer line, so it states no confidence and reports no option probabilities. It has no answers kept at a confidence threshold, no calibration gap, ranking score (AUROC) or Brier score, and no typical score of a right or wrong answer.

Repeats

We did not repeat this setup.

Latency

Latency, median request
32.2 s (this run)
Latency, 90th percentile
74.8 s
Requests at once
32
Throughput
46.4 questions per minute of request time
Request time
47.3 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
$0.894$894
Whole run
$1.96
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
266
Output tokens per question
2,186