Decision model

GLiDE 27B

1 question per request

Accuracy, all 2,198 questions
71.1%69.2% to 73.0%, 95% interval; 1,563 right
Answers kept at 99% confidence
247 of 2,1980 wrong; share right 98.5% to 100.0%, 95% interval
Cost, $ per 1,000 questionsper 1M questions
No list priceBasis and price under Cost
Latency
0.542 smedian request, 1 question per request

Back to the leaderboard.

How we called it

Kind
Decision model
Access
GLiDE server (Fastino's release code), self-hosted
Paid as
Our own hardware
Model ID
glide-27b
Variant
local
Parameters
27B dense, as the maker states it (counted from the released files: 26.09B).language model (no LM head) + 0.46B vision encoder + 255-way readout; source: counted from the checkpoint's safetensors, fastino/GLiDE-27B@4d32743, huggingface.co/fastino/GLiDE-27B; read 10 November 2026
Hardware
1 × DGX Spark, GB10 (128 GB unified memory); BF16
Note
Fastino's released GLiDE 27B (fastino/GLiDE-27B at 4d32743, 5 November 2026), a modified Qwen3.8-27B whose layers 24 to 47 run twice (recurrent depth, its decision_config.json), run on our hardware through the server it ships. The same repository's earlier checkpoint, kept at its tag glide-v1.2, is the GLiDE · v1.2 row.
Confidence from
Option score
Run
899, 10 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
ce3fd5527feb
Prompt version
254597b8be16

Results

QuestionsAccuracy95% intervalRight
All questions71.1%69.2% to 73.0%1,563 of 2,198
Reading90.9%88.4% to 92.8%596 of 656
Grammar62.7%60.3% to 65.1%967 of 1,542

Comparison group: yzAC. Compare with another setup.

Accuracy by topic
TopicPartAccuracyRight
Word and phrase meaningsReading91.6%120 of 131
Sentence meaningsReading94.8%146 of 154
How a writer explains and develops ideasReading85.7%60 of 70
Topic and main point of a paragraphReading92.9%91 of 98
How a paragraph fits togetherReading82.1%87 of 106
Details that support a paragraph’s main pointReading94.8%92 of 97
Word types, such as nouns and verbsGrammar69.3%97 of 140
Groups of words built around a nounGrammar64.6%42 of 65
Verbs and their formsGrammar68.1%62 of 91
Verb forms used like nouns or modifiersGrammar79.2%57 of 72
Word endings and what they doGrammar62.0%49 of 79
How words are builtGrammar46.4%32 of 69
The roles of words and phrases in a sentenceGrammar63.4%92 of 145
How verbs show who acts and who receives the actionGrammar75.7%56 of 74
Types of sentencesGrammar62.4%53 of 85
Questions combining several grammar topicsGrammar49.1%108 of 220
Sound patterns and changesGrammar32.5%25 of 77
SpellingGrammar63.9%85 of 133
PunctuationGrammar64.1%75 of 117
Problems in sentence wordingGrammar76.6%134 of 175

Vision (preliminary)

Preliminary: these numbers are not final and may change. This setup is condition A of the Vision tab, which asks the 763 questions with underlined or numbered words as text (A), as a page image (B), as both (C) and through OCR models (D); the share answered right, its 95% interval in the number's tooltip.

ModelA · text onlyaccuracy, higher is betterB · image onlyaccuracy, higher is betterC · text plus imageaccuracy, higher is betterBest OCR routeaccuracy, higher is better
GLiDE 27B Open · 27B69.1%49.9%68.8%64.2%via Surya OCR 2

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
497 of 547, first English run (901)
Accuracy
90.9%
Non-hallucination with “I don't know”
37.9%: 22 “I don't know” of 58 not right (run 903)
Answered with “I don't know”
96.0%: 525 of 547
Error rate with “I don't know”
6.9%: 36 of 525 answers
Cost, $ per 1,000 questionsper 1M questions, first English run
No list price
Latency, median request, first English run
0.545 s; 1 request at once
English run
901
Machine, English runs
DGX Spark
Date
10 November 2026
Request format
1 question per request
Reasoning
off
Prompt version
47f5776e71db
Translations, SHA-256
bf0d47cd385a93050c65906977e199ef7e45d5848dbbdef2bc8d124f4d5abf68

Confidence

Answers kept at 99% or more
247, of which 0 wrong (share right: 98.5% to 100.0%, 95% interval); 1,951 skipped, the model less than 99% sure
Calibration gap
2.3 points
AUROC, all questions
0.84 0.83 to 0.86
AUROC, reading
0.93 0.90 to 0.95
AUROC, grammar
0.78 0.76 to 0.81
Brier score
0.144
Accuracy of its surest answers
most confident fifth: 100.0% right; most confident half: 93.0% right; most confident four fifths: 80.1% right
Typical score of a right answer
88.2%
Typical score of a wrong answer
49.0%

Repeats

We did not repeat this setup.

Latency

Latency, median request
0.542 s (this run)
Latency, 90th percentile
0.676 s
Requests at once
1
Throughput
106.1 questions per minute of request time
Request time
20.7 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
No list price
Basis
No dollar estimate; see hardware and time
Input tokens per question
359
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 · chat27.1%−0.06 points27%†
GPT-6 Astra high · chat28.5%−0.10 points29%†
GPT-6.1 Sol high · chat29.6%−0.10 points30%†
GPT-6 Astra low · chat28.5%−0.10 points29%†
GPT-6 Astra low · chat · 1 per request27.4%−0.08 points27%†
Gemini 3.8 Flash low · chat · 1 per request29.9%−0.07 points30%†
GPT-6.1 Sol low · chat · 1 per request32.4%−0.13 points32%†
GPT-6.1 Sol low · chat28.5%−0.10 points29%†
Claude Opus 5.5 high · chat30.7%−0.19 points31%†
GPT-6.1 Terra high · chat30.2%−0.13 points30%†
Claude Opus 5.5 low · chat · 1 per request29.5%−0.10 points30%†
Gemini 3.8 Flash low · chat27.8%−0.12 points28%†
GPT-6.1 Terra low · chat35.4%−0.10 points35%†
Claude Opus 5.5 low · chat35.5%−0.14 points36%†
Claude Sonnet 5.5 high · chat · 1 per request34.5%−0.10 points35%†
Claude Sonnet 5.5 high · chat56.0%−0.14 points56%†

† Leaves out the first model’s hardware cost, which we have not estimated.