Decision model

Perplexity Decider Flash v1.3

1 question per request

Accuracy, all 2,198 questions
49.7%47.6% to 51.8%, 95% interval; 1,093 right
Answers kept at 99% confidence
29 of 2,1980 wrong; share right 88.3% to 100.0%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
$0.025$24.69Basis and price under Cost
Latency
0.033 smedian request, 1 question per request

Back to the leaderboard.

Perplexity Decider 27B v1.2 · API and Perplexity Decider 27B v1.2 · API · with web, with Perplexity's web search off and on, are compared on Web grounding.

How we called it

Kind
Decision model
Access
Perplexity Decider server, self-hosted
Paid as
Our own hardware
Model ID
pplx-decider-flash-v1.3
Variant
local
Parameters
4B dense, as the maker states it (counted from the released files: 4.54B).language model (tied embeddings) + vision encoder + 255-way readout; its locate-span adapter and head (0.13B), used only by its locate task, not counted; source: counted from the checkpoint's safetensors, perplexity-ai/pplx-decider-flash-v1.3@d06fb3f, huggingface.co/perplexity-ai/pplx-decider-flash-v1.3; read 9 November 2026
Hardware
1 × RTX PRO 6000 Blackwell (96 GB); BF16
Note
Perplexity's released Flash v1.3 checkpoint, distilled from Decider 27B v1.3 on Qwen3.5-4B, run on our hardware through the package it ships.
Confidence from
Option score
Run
1123, 14 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
5424d93c2c6c
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions49.7%47.6% to 51.8%1,093 of 2,198
Reading74.4%70.9% to 77.6%488 of 656
Grammar39.2%36.8% to 41.7%605 of 1,542

Comparison group: βγδζηθ. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading63.4%83 of 131
Sentence meaningsReading81.8%126 of 154
How a writer explains and develops ideasReading71.4%50 of 70
Topic and main point of a paragraphReading85.7%84 of 98
How a paragraph fits togetherReading65.1%69 of 106
Details that support a paragraph’s main pointReading78.4%76 of 97
Word types, such as nouns and verbsGrammar45.7%64 of 140
Groups of words built around a nounGrammar43.1%28 of 65
Verbs and their formsGrammar35.2%32 of 91
Verb forms used like nouns or modifiersGrammar44.4%32 of 72
Word endings and what they doGrammar44.3%35 of 79
How words are builtGrammar29.0%20 of 69
The roles of words and phrases in a sentenceGrammar39.3%57 of 145
How verbs show who acts and who receives the actionGrammar41.9%31 of 74
Types of sentencesGrammar35.3%30 of 85
Questions combining several grammar topicsGrammar34.1%75 of 220
Sound patterns and changesGrammar24.7%19 of 77
SpellingGrammar29.3%39 of 133
PunctuationGrammar42.7%50 of 117
Problems in sentence wordingGrammar53.1%93 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
458 of 547, first English run (1126)
Accuracy
83.7%
Non-hallucination with “I don't know”
7.2%: 7 “I don't know” of 97 not right (run 1128)
Answered with “I don't know”
98.7%: 540 of 547
Error rate with “I don't know”
16.7%: 90 of 540 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
0.02323.17from GPU time
Latency, median request, first English run
0.033 s; 1 request at once
English run
1126
Machine, English runs
RTX PRO 6000
Date
14 November 2026
Request format
1 question per request
Reasoning
off
Prompt version
47f5776e71db
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

Confidence

Answers kept at 99% or more
29, of which 0 wrong (share right: 88.3% to 100.0%, 95% interval); 2,169 skipped, the model less than 99% sure
Calibration gap
12.6 points
AUROC, all questions
0.74 0.72 to 0.76
AUROC, reading
0.83 0.80 to 0.86
AUROC, grammar
0.64 0.61 to 0.67
Brier score
0.221
Accuracy of its surest answers
most confident fifth: 89.6% right; most confident half: 66.0% right; most confident four fifths: 55.1% right
Typical score of a right answer
79.0%
Typical score of a wrong answer
48.8%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.033 s (this run)
Latency, 90th percentile
0.049 s
Requests at once
1
Throughput
1681.0 questions per minute of request time
Request time
1.3 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
$0.025$24.69
Whole run
$0.054
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
372
Output tokens per question
0

Going first in front of an LLM

Replay of recorded answers, cutoff chosen on half the questions, averaged over the splits. Savings are estimates from API prices; the Method page explains how.

LLM behind itShare takenAccuracy changeSaving
Gemini 3.8 Flash high · chat8.7%−0.09 points8%
GPT-6 Astra high · chat8.7%−0.09 points8%
GPT-6.1 Sol high · chat8.7%−0.09 points7%
GPT-6 Astra low · chat8.8%−0.09 points8%
GPT-6 Astra low · chat · 1 per request8.7%−0.09 points9%
Gemini 3.8 Flash low · chat · 1 per request8.8%−0.10 points6%
GPT-6.1 Sol low · chat · 1 per request8.8%−0.10 points8%
GPT-6.1 Sol low · chat8.8%−0.09 points7%
Claude Opus 5.5 high · chat8.8%−0.09 points8%
GPT-6.1 Terra high · chat8.7%−0.09 points4%
Claude Opus 5.5 low · chat · 1 per request8.8%−0.09 points9%
Gemini 3.8 Flash low · chat8.8%−0.10 points-0%
GPT-6.1 Terra low · chat8.9%−0.10 points3%
Claude Opus 5.5 low · chat8.8%−0.09 points8%
Claude Sonnet 5.5 high · chat · 1 per request9.3%−0.09 points9%
Claude Sonnet 5.5 high · chat12.3%−0.12 points12%