Chat model

Qwen3.5-2B reasoning off · chat

reasoning off · 1 question per request

Accuracy, all 2,198 questions
25.4%23.6% to 27.2%, 95% interval; 558 right
Answers kept at 99% confidence
Not measureda plain answer line, no confidence
Cost, $ per 1,000 questionsper 1M questions
$0.268$268Basis and price under Cost
Latency
8.84 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/Qwen3.5-2B@15852e8), 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
qwen3.5-2b-nothink
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, Qwen/Qwen3.5-2B@15852e8, huggingface.co/Qwen/Qwen3.5-2B; read 15 November 2026
Hardware
1 × RTX PRO 6000 Blackwell (96 GB); BF16
Confidence from
Not measureda plain answer line, no confidence
Run
1218, 15 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
7bc1f66c76b0
Prompt version
ba455bb00e5c

Results

QuestionsAccuracy95% intervalRight
All questions25.4%23.6% to 27.2%558 of 2,198
Reading34.3%30.8% to 38.0%225 of 656
Grammar21.6%19.6% to 23.7%333 of 1,542

Comparison group: ψΓΔΘ. Compare with another setup.

Invalid answers: 154; read from broken replies: 0; empty replies asked again: 0. Still invalid: 8 cut off at the output limit, 146 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 1219): Invalid answers: 221; read from broken replies: 0; empty replies asked again: 0. Still invalid: 5 cut off at the output limit, 216 unreadable. (how)

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading29.8%39 of 131
Sentence meaningsReading35.7%55 of 154
How a writer explains and develops ideasReading25.7%18 of 70
Topic and main point of a paragraphReading48.0%47 of 98
How a paragraph fits togetherReading31.1%33 of 106
Details that support a paragraph’s main pointReading34.0%33 of 97
Word types, such as nouns and verbsGrammar20.7%29 of 140
Groups of words built around a nounGrammar18.5%12 of 65
Verbs and their formsGrammar18.7%17 of 91
Verb forms used like nouns or modifiersGrammar27.8%20 of 72
Word endings and what they doGrammar20.3%16 of 79
How words are builtGrammar18.8%13 of 69
The roles of words and phrases in a sentenceGrammar23.4%34 of 145
How verbs show who acts and who receives the actionGrammar21.6%16 of 74
Types of sentencesGrammar18.8%16 of 85
Questions combining several grammar topicsGrammar21.8%48 of 220
Sound patterns and changesGrammar16.9%13 of 77
SpellingGrammar18.0%24 of 133
PunctuationGrammar17.9%21 of 117
Problems in sentence wordingGrammar30.9%54 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
368 of 547, first English run (1215)
Accuracy
67.3%
Non-hallucination with “I don't know”
10.3%: 18 “I don't know” of 174 not right (run 1216)
Answered with “I don't know”
96.3%: 527 of 547
Error rate with “I don't know”
29.6%: 156 of 527 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.280280from GPU time
Latency, median request, first English run
9.27 s; 32 requests at once
English run
1215
Machine, English runs
RTX PRO 6000
Date
15 November 2026
Request format
1 question per request
Reasoning
off
Prompt version
ad6f4cc346df
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

With “I don't know” (run 1216): Invalid answers: 2; read from broken replies: 0; empty replies asked again: 0. Still invalid: 2 unreadable. (how)

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
8.84 s (this run)
Latency, 90th percentile
20.1 s
Requests at once
32
Throughput
155.1 questions per minute of request time
Request time
14.2 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
$0.268$268
Whole run
$0.59
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
266
Output tokens per question
1,278