Chat model

DeepSeek-V4.1-Flash reasoning on · chat · 1017

reasoning on · 16 questions per request

Accuracy, all 2,198 questions
91.8%90.5% to 92.8%, 95% interval; 2,017 right
Answers kept at 99% confidence
2,164 of 2,198149 wrong; share right 92.0% to 94.1%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
$1.278$1,278Basis and price under Cost
Latency
486.9 smedian request, 16 questions per request

Back to the leaderboard.

How we called it

Kind
Chat model
Access
SGLang, self-hosted, published mixed precision; 1017 weights (revision 1bae0e1)
Paid as
Our own hardware
Model ID
deepseek-v4.1-flash-1017
Parameters
Mixture of experts: 552B total, about 16B active per step. Size class uses the total (552B).V4.1 Flash card (first release): 552B backbone + 196B conditional memory; 8B active in prefill, 16B in decode; the 1017 card states no size; pages checked: huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017, huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash; read 9 November 2026
Hardware
4 × RTX PRO 6000 Blackwell (96 GB); FP4 experts, FP8 and BF16 layers
Confidence from
Answer letter probability
Run
585, 5 November 2026

Settings

Reasoning
on
Request format
16 questions per request
Requests at once
8
Temperature
not recorded
Run record: harness seed, harness commit and prompt version
Harness seed
0
Harness commit
d4268ef9b103
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions91.8%90.5% to 92.8%2,017 of 2,198
Reading94.1%92.0% to 95.6%617 of 656
Grammar90.8%89.2% to 92.1%1,400 of 1,542

Comparison group: jkl. Compare with another setup.

Invalid answers: 32; read from broken replies: 0; empty replies asked again: 0. Still invalid: 16 empty and not yet asked again, 16 cut off at the output limit. 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).

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading93.9%123 of 131
Sentence meaningsReading98.7%152 of 154
How a writer explains and develops ideasReading90.0%63 of 70
Topic and main point of a paragraphReading94.9%93 of 98
How a paragraph fits togetherReading87.7%93 of 106
Details that support a paragraph’s main pointReading95.9%93 of 97
Word types, such as nouns and verbsGrammar95.7%134 of 140
Groups of words built around a nounGrammar98.5%64 of 65
Verbs and their formsGrammar97.8%89 of 91
Verb forms used like nouns or modifiersGrammar98.6%71 of 72
Word endings and what they doGrammar96.2%76 of 79
How words are builtGrammar88.4%61 of 69
The roles of words and phrases in a sentenceGrammar95.2%138 of 145
How verbs show who acts and who receives the actionGrammar93.2%69 of 74
Types of sentencesGrammar97.6%83 of 85
Questions combining several grammar topicsGrammar75.0%165 of 220
Sound patterns and changesGrammar87.0%67 of 77
SpellingGrammar91.7%122 of 133
PunctuationGrammar88.0%103 of 117
Problems in sentence wordingGrammar90.3%158 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
506 of 547, first English run (808)
Accuracy
92.5%
Non-hallucination with “I don't know”
7.1%: 3 “I don't know” of 42 not right (run 809)
Answered with “I don't know”
99.5%: 544 of 547
Error rate with “I don't know”
7.2%: 39 of 544 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.421421at the maker's list price
Latency, median request, first English run
189.4 s; 8 requests at once
English run
808
Machine, English runs
RTX PRO 6000
Date
5 November 2026
Request format
16 questions per request
Reasoning
on
Prompt version
5c3a4849752e
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

Confidence

Answers kept at 99% or more
2,164, of which 149 wrong (share right: 92.0% to 94.1%, 95% interval); 34 skipped: 2 with the model less than 99% sure and 32 without a valid answer
Calibration gap
6.9 points
AUROC, all questions
0.61 0.57 to 0.66
AUROC, reading
0.61 0.51 to 0.70
AUROC, grammar
0.62 0.56 to 0.68
Brier score
0.069
Accuracy of its surest answers
most confident fifth: 95.4% right; most confident half: 95.5% right; most confident four fifths: 94.2% right
Typical score of a right answer
100.0%
Typical score of a wrong answer
100.0%

Repeats

Run 5 times on a sample of 200 questions.

Answers changed in 5 runs
15 of 200
Same wrong answer in all 5
1 of 200
Wrong in at least one run
16 of 200
Accuracy in each run
96.5%, 94.5%, 97.0%, 95.0%, 96.0%

Latency

Latency, median request
486.9 s (this run)
Latency, 90th percentile
1129.4 s
Requests at once
8
Throughput
12.9 questions per minute of request time
Request time
170.9 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
$1.278$1,278
Whole run
$2.81
Basis
Estimated at DeepSeek's list price for the same model; our hardware cost is not measured.
Price
$0.30 input, $0.006 cached input, $1.20 output per 1M tokens (source, 2026-11-05)
Input tokens per question
305
Output tokens per question
989