Chat model

Qwen3.5-4B reasoning on · chat

reasoning on · 1 question per request

Accuracy, all 2,198 questions
58.9%56.8% to 61.0%, 95% interval; 1,295 right
Answers kept at 99% confidence
Not measureda plain answer line, no confidence
Cost, $ per 1,000 questionsper 1M questions
$2.998$2,998Basis and price under Cost
Latency
140.3 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 on; output cap 32,768
Paid as
Our own hardware
Model ID
qwen3.5-4b
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
1149, 14 November 2026

Settings

Reasoning
on
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 questions58.9%56.8% to 61.0%1,295 of 2,198
Reading79.1%75.8% to 82.1%519 of 656
Grammar50.3%47.8% to 52.8%776 of 1,542

Comparison group: PQRSTUVW. Compare with another setup.

Invalid answers: 5; read from broken replies: 0; empty replies asked again: 0. Still invalid: 1 cut off at the output limit, 4 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 1150): Invalid answers: 5; read from broken replies: 0; empty replies asked again: 0. Still invalid: 2 cut off at the output limit, 3 unreadable. (how)

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading67.2%88 of 131
Sentence meaningsReading87.7%135 of 154
How a writer explains and develops ideasReading71.4%50 of 70
Topic and main point of a paragraphReading91.8%90 of 98
How a paragraph fits togetherReading72.6%77 of 106
Details that support a paragraph’s main pointReading81.4%79 of 97
Word types, such as nouns and verbsGrammar56.4%79 of 140
Groups of words built around a nounGrammar50.8%33 of 65
Verbs and their formsGrammar58.2%53 of 91
Verb forms used like nouns or modifiersGrammar65.3%47 of 72
Word endings and what they doGrammar46.8%37 of 79
How words are builtGrammar44.9%31 of 69
The roles of words and phrases in a sentenceGrammar53.8%78 of 145
How verbs show who acts and who receives the actionGrammar67.6%50 of 74
Types of sentencesGrammar54.1%46 of 85
Questions combining several grammar topicsGrammar36.8%81 of 220
Sound patterns and changesGrammar26.0%20 of 77
SpellingGrammar40.6%54 of 133
PunctuationGrammar51.3%60 of 117
Problems in sentence wordingGrammar61.1%107 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
476 of 547, first English run (1072)
Accuracy
87.0%
Non-hallucination with “I don't know”
2.4%: 2 “I don't know” of 85 not right (run 1073)
Answered with “I don't know”
99.6%: 545 of 547
Error rate with “I don't know”
15.2%: 83 of 545 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
1.3901,390from GPU time
Latency, median request, first English run
58.3 s; 32 requests at once
English run
1072
Machine, English runs
RTX PRO 6000
Date
13 November 2026
Request format
1 question per request
Reasoning
on
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
140.3 s (this run)
Latency, 90th percentile
204.2 s
Requests at once
32
Throughput
13.8 questions per minute of request time
Request time
158.8 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
$2.998$2,998
Whole run
$6.59
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
264
Output tokens per question
7,397