Preply Progress Dashboard

Results

Select a Student

Latest Progress Index70.0

+16.3 vs baseline

Best Lesson3

70.0 peak score

Lessons Tracked3

Full chronological progression

Progress Trend

Subscore Trend

Lesson Breakdown

Lesson

1

Progress Index 53.7

quiz_grammarguided_practicecontains_readingmixed_reading_speaking

Fluency35.6

Accuracy92.6

Complexity22.7

Lexical Range49.0

Engagement75.5

Reading share21.9%

Baseline in 1 is 53.7. Most visible signals are Accuracy, Complexity, Engagement. Main score is based on speaking turns only; reading activity is tracked separately.

Top drivers: Accuracy, Complexity, Engagement

Lesson

2

Progress Index 52.9

quiz_grammarguided_practice

Fluency-2.7

Accuracy+4.2

Complexity+7.8

Lexical Range-28.2

Engagement-0.7

In 2, progress held mostly flat to 52.9 (-0.9 vs previous, -0.9 vs baseline). Biggest drivers were Lexical Range, Complexity, Accuracy.

Top drivers: Lexical Range, Complexity, Accuracy

Lesson

3

Progress Index 70.0

guided_practice

Fluency+10.4

Accuracy-0.3

Complexity+31.8

Lexical Range+41.0

Engagement+14.0

In 3, progress rose to 70.0 (+17.1 vs previous, +16.3 vs baseline). Biggest drivers were Lexical Range, Complexity, Engagement.

Top drivers: Lexical Range, Complexity, Engagement

Sound More Native

Transcript-grounded suggestions for each lesson — real quotes from the student with concrete rewrites and micro-tips.

Sound More Native

You're communicating clearly and showing real progress - here are three small tweaks that will make you sound much more natural right away.

Article / PrepositionEasy win #1

×Give me moment because, I don't have, I don't have, to write, you know, paper.

Try this instead

✓Give me a moment because I don't have anything to write with.

Just adding the article 'a' before 'moment' and replacing 'paper' with 'paper to write on' (or 'anything to write with') fixes two very common small errors in one short sentence.

Micro tip: Singular countable nouns in English almost always need 'a' or 'the' in front of them - 'a moment', 'a pen', 'a second'.

Article / PrepositionEasy win #2

×See you see you, in lunchtime.

Try this instead

✓See you at lunchtime.

Swapping one preposition ('in' -> 'at') is a tiny one-word fix that immediately sounds native.

Micro tip: Use 'at' with mealtimes and clock times: 'at lunchtime', 'at dinner', 'at 7PM'.

TenseEasy win #3

×She is the artist who paint the beautiful Mora Decade, which I bought last year.

Try this instead

✓She is the artist who painted the beautiful Mora Decade, which I bought last year.

The verb after a relative pronoun must agree with its subject - 'who' refers to 'she' (third person singular), so just adding an 's' gives 'paints', which is a one-letter fix.

Micro tip: After 'who' in a relative clause, the verb still needs its normal subject-verb agreement: 'the artist who paints', 'the man who works'.

Lesson Metrics

Always visibleHeadline score

Metric	1	2	3
Progress Index i What it shows: The overall speaking-based lesson score used to compare the student across lessons. How we measure it: Each raw metric is mapped to 0-100 using fixed anchors (not cohort-relative), then combined into five subscores and rolled up as 25% Fluency, 25% Accuracy, 20% Complexity, 15% Lexical Range, and 15% Engagement. Reading turns are tracked separately and excluded.	53.742	52.878	70.016

Fluency & flow8 metrics

Metric	1	2	3
Student WPM i What it shows: How fast the student produced alphabetic words during speaking turns only. How we measure it: Speaking alpha-token count divided by speaking-turn minutes. Reading turns are excluded and shown separately in the reading activity section.	44.145	49.764	83.356
Student Talk Ratio (%) i What it shows: How much of the speaking-focused lesson word volume came from the student instead of the tutor. How we measure it: 100 times speaking student alpha tokens divided by speaking student alpha tokens plus tutor alpha tokens from speaking-focused interactions.	59.44	34.874	68.324
Avg Turn Words i What it shows: How much the student tends to say each time they take a speaking turn. How we measure it: Mean alphabetic word count per speaking student turn, recomputed over the lesson from speaking-only turns.	19.594	21.721	43.141
Response Latency (s) i What it shows: How quickly the student answers after the tutor finishes speaking in speaking-focused exchanges. How we measure it: Median gap in seconds between a tutor turn ending and the next student speaking turn beginning, recomputed over the full lesson timeline.	0.265	0	0
Long Pauses >1s i What it shows: How often there is a noticeable pause in the student's speaking flow. How we measure it: Count of gaps greater than 1.0 second between consecutive speaking alpha tokens inside speaking turns, using word-level timestamps.	215	209	253
Filler Ratio (%) i What it shows: How much the student relies on filler words such as um, uh, erm, hmm, or like while speaking. How we measure it: 100 times filler-word tokens divided by speaking alpha tokens. This is separate from the broader disfluency metric, which also includes immediate repetitions.	0.653	0.988	0.893
Pronunciation Clarity (ASR) i What it shows: A proxy for pronunciation clarity and accent. When the ASR system is less confident, the student's speech is usually harder for a listener to follow too. How we measure it: Mean word-level ASR confidence across the student's speaking tokens. Anchored to 0.70 → 0 and 0.97 → 100 in the Engagement subscore.	0.892	0.942	0.939
Low-Confidence Words (%) i What it shows: How much of the student's speaking the ASR system considered comparatively uncertain. How we measure it: 100 times speaking alpha tokens with ASR confidence below 0.90 divided by all speaking alpha tokens that include a confidence score.	31.69	19.075	19.61

Accuracy & mistakes6 metrics

Metric	1	2	3
Mistakes (total) i What it shows: How many transcript-visible mistakes were flagged in the student's speaking turns for this lesson. How we measure it: Count of detections from the rule-based grammar checker (and optionally the LLM-enhanced pass) across all student speaking turns in the lesson.	2	2	3
Mistakes T1 (Core) i What it shows: Tier-1 core errors signal missing A2-level foundations and weigh heaviest in the Accuracy subscore. How we measure it: Count of detected mistakes labeled tier_1_core, such as subject-verb agreement slips, double negatives, or `I am agree`.	2	1	0
Mistakes T2 (Intermediate) i What it shows: Tier-2 errors in B1-B2 structures such as perfect tenses, prepositions, or second conditionals. How we measure it: Count of detected mistakes labeled tier_2_intermediate.	0	1	3
Mistakes T3 (Stretch) i What it shows: Tier-3 errors in C1+ structures the student is stretching into; weighted lightly. How we measure it: Count of detected mistakes labeled tier_3_stretch (mostly surfaced by the LLM-enhanced pass, rarely by rules).	0	0	0
Weighted Error Rate (per 100w) i What it shows: Raw Accuracy input — tier-weighted mistakes normalized to a per-100-word rate. How we measure it: (3 × T1 + 2 × T2 + 1 × T3) ÷ speaking alpha tokens × 100.	0.435	0.26	0.162
Tutor Correction Rate (%) i What it shows: How much direct tutor correction or scaffolding showed up during speaking-focused interactions. Shown as supplementary context — no longer part of the Progress Index because tutor style and student confidence both distort it. How we measure it: 100 times tutor correction-marker matches divided by tutor alpha tokens in speaking-focused interactions, using markers like you should, say, better, instead, remember, correct, mistake, pronounce, repeat, and means.	0.425	1.141	0.642

Complexity5 metrics

Metric	1	2	3
Avg Sentence Length i What it shows: How long the student's speaking sentences are on average. How we measure it: Mean alphabetic token count per detected speaking sentence, recomputed over the lesson from speaking-only sentences.	4.178	4.693	9.079
Sentences 10+ Words i What it shows: How many student sentences are at least ten words long. How we measure it: Count of detected student sentences whose alphabetic token count is 10 or more, summed across the lesson.	29	67	151
Complex Words (6+ chars) i What it shows: How often the student uses longer, more information-dense word forms while speaking. How we measure it: Count of speaking alpha tokens with 6 or more characters after deterministic cleanup and repeat collapsing.	218	281	734
Long Words (8+ chars %) i What it shows: The share of speaking words that are especially long. How we measure it: 100 times speaking alpha tokens with 8 or more characters divided by all speaking alpha tokens.	5.874	5.042	8.493
Complex Sentence Rate (%) i What it shows: How often the student uses speaking sentences with linking or subordinating structure. How we measure it: Percentage of speaking sentences containing connector markers such as because, although, while, if, when, which, but, so, therefore, or since.	8.434	17.275	37.685

Lexical range1 metric

Metric	1	2	3
MATTR-50 i What it shows: Vocabulary variety in the student's speaking turns, with less distortion from lesson length than a simple unique-word ratio. How we measure it: Moving-average type-token ratio over 50-word windows from speaking tokens only; if there are fewer than 50 speaking words, we fall back to unique tokens divided by total tokens.	0.629	0.508	0.673

Engagement signal1 metric

Metric	1	2	3
Elaboration Depth i What it shows: How much detail the student gives after open tutor prompts when responding in speaking mode. How we measure it: Average speaking-response length in words after tutor prompts such as why, how, tell me, or describe.	6.308	9.171	17.879

Reading activity5 metrics

Metric	1	2	3
Reading Turns i What it shows: How many student turns in the lesson were classified as reading aloud rather than free speaking. How we measure it: Count of student dialogue turns labeled as reading after the reading-vs-speaking classifier runs on the lesson transcript.	21	0	0
Reading Alpha Tokens i What it shows: How much student word volume came from reading aloud. How we measure it: Count of alphabetic student tokens assigned to reading turns after repeat collapsing.	386	0	0
Reading Duration (s) i What it shows: How much lesson time the student spent reading aloud. How we measure it: Sum of durations for student turns labeled as reading.	407.86	0	0
Reading WPM i What it shows: How fast the student read aloud during reading turns. How we measure it: Reading alpha-token count divided by reading-turn minutes. This is tracked separately from speaking WPM and does not affect the Progress Index.	56.784	0	0
Reading Share (%) i What it shows: What share of the student's total word volume came from reading aloud. How we measure it: 100 times reading alpha tokens divided by all student alpha tokens from both speaking and reading turns.	21.87	0	0

Latest Progress Index67.7

-1.9 vs baseline

Best Lesson1

69.6 peak score

Lessons Tracked2

Full chronological progression

Progress Trend

Subscore Trend

Lesson Breakdown

Lesson

1

Progress Index 69.6

guided_practice

Fluency38.4

Accuracy97.3

Complexity59.6

Lexical Range75.4

Engagement83.0

Baseline in 1 is 69.6. Most visible signals are Accuracy, Engagement, Lexical Range.

Top drivers: Accuracy, Engagement, Lexical Range

Lesson

2

Progress Index 67.7

guided_practice

Fluency-0.5

Accuracy-1.8

Complexity+6.1

Lexical Range-13.2

Engagement-1.3

In 2, progress declined to 67.7 (-1.9 vs previous, -1.9 vs baseline). Biggest drivers were Lexical Range, Complexity, Accuracy.

Top drivers: Lexical Range, Complexity, Accuracy

Sound More Native

Transcript-grounded suggestions for each lesson — real quotes from the student with concrete rewrites and micro-tips.

Sound More Native

You speak with impressive fluency and passion - three small tweaks will make you sound even more natural right away.

Natural PhraseEasy win #1

×But on the end, you're winning.

Try this instead

✓But in the end, you're winning.

Swapping one preposition turns a very common learner phrase into the standard English idiom - no restructuring needed.

Micro tip: Always use 'in the end' (not 'on the end') when you mean 'ultimately' or 'finally'.

TenseEasy win #2

×Last year, there was no snow at all, and I I never been skiing, last year.

Try this instead

✓Last year, there was no snow at all, and I had never been skiing last year.

Adding one word ('had') fixes the tense and makes the sentence immediately correct - the rest of the sentence stays the same.

Micro tip: When you talk about something that didn't happen before a past point in time, use 'had never' (past perfect), not 'never been'.

Word ChoiceEasy win #3

×I'm very gracious to to to Ukraine to Ukraine people.

Try this instead

✓I'm very grateful to the Ukrainian people.

Replacing one word fixes a false-friend error - 'gracious' means polite/kind, while 'grateful' is the word for feeling thankful.

Micro tip: Use 'grateful to someone' when you feel thankful; 'gracious' describes how you behave toward others, not how you feel.

Lesson Metrics

Always visibleHeadline score

Metric	1	2
Progress Index i What it shows: The overall speaking-based lesson score used to compare the student across lessons. How we measure it: Each raw metric is mapped to 0-100 using fixed anchors (not cohort-relative), then combined into five subscores and rolled up as 25% Fluency, 25% Accuracy, 20% Complexity, 15% Lexical Range, and 15% Engagement. Reading turns are tracked separately and excluded.	69.581	67.676

Fluency & flow8 metrics

Metric	1	2
Student WPM i What it shows: How fast the student produced alphabetic words during speaking turns only. How we measure it: Speaking alpha-token count divided by speaking-turn minutes. Reading turns are excluded and shown separately in the reading activity section.	93.934	93.017
Student Talk Ratio (%) i What it shows: How much of the speaking-focused lesson word volume came from the student instead of the tutor. How we measure it: 100 times speaking student alpha tokens divided by speaking student alpha tokens plus tutor alpha tokens from speaking-focused interactions.	69.393	60.475
Avg Turn Words i What it shows: How much the student tends to say each time they take a speaking turn. How we measure it: Mean alphabetic word count per speaking student turn, recomputed over the lesson from speaking-only turns.	44	49.674
Response Latency (s) i What it shows: How quickly the student answers after the tutor finishes speaking in speaking-focused exchanges. How we measure it: Median gap in seconds between a tutor turn ending and the next student speaking turn beginning, recomputed over the full lesson timeline.	0	0
Long Pauses >1s i What it shows: How often there is a noticeable pause in the student's speaking flow. How we measure it: Count of gaps greater than 1.0 second between consecutive speaking alpha tokens inside speaking turns, using word-level timestamps.	373	243
Filler Ratio (%) i What it shows: How much the student relies on filler words such as um, uh, erm, hmm, or like while speaking. How we measure it: 100 times filler-word tokens divided by speaking alpha tokens. This is separate from the broader disfluency metric, which also includes immediate repetitions.	0.917	1.017
Pronunciation Clarity (ASR) i What it shows: A proxy for pronunciation clarity and accent. When the ASR system is less confident, the student's speech is usually harder for a listener to follow too. How we measure it: Mean word-level ASR confidence across the student's speaking tokens. Anchored to 0.70 → 0 and 0.97 → 100 in the Engagement subscore.	0.912	0.932
Low-Confidence Words (%) i What it shows: How much of the student's speaking the ASR system considered comparatively uncertain. How we measure it: 100 times speaking alpha tokens with ASR confidence below 0.90 divided by all speaking alpha tokens that include a confidence score.	26.747	20.684

Accuracy & mistakes6 metrics

Metric	1	2
Mistakes (total) i What it shows: How many transcript-visible mistakes were flagged in the student's speaking turns for this lesson. How we measure it: Count of detections from the rule-based grammar checker (and optionally the LLM-enhanced pass) across all student speaking turns in the lesson.	2	3
Mistakes T1 (Core) i What it shows: Tier-1 core errors signal missing A2-level foundations and weigh heaviest in the Accuracy subscore. How we measure it: Count of detected mistakes labeled tier_1_core, such as subject-verb agreement slips, double negatives, or `I am agree`.	1	3
Mistakes T2 (Intermediate) i What it shows: Tier-2 errors in B1-B2 structures such as perfect tenses, prepositions, or second conditionals. How we measure it: Count of detected mistakes labeled tier_2_intermediate.	1	0
Mistakes T3 (Stretch) i What it shows: Tier-3 errors in C1+ structures the student is stretching into; weighted lightly. How we measure it: Count of detected mistakes labeled tier_3_stretch (mostly surfaced by the LLM-enhanced pass, rarely by rules).	0	0
Weighted Error Rate (per 100w) i What it shows: Raw Accuracy input — tier-weighted mistakes normalized to a per-100-word rate. How we measure it: (3 × T1 + 2 × T2 + 1 × T3) ÷ speaking alpha tokens × 100.	0.118	0.208
Tutor Correction Rate (%) i What it shows: How much direct tutor correction or scaffolding showed up during speaking-focused interactions. Shown as supplementary context — no longer part of the Progress Index because tutor style and student confidence both distort it. How we measure it: 100 times tutor correction-marker matches divided by tutor alpha tokens in speaking-focused interactions, using markers like you should, say, better, instead, remember, correct, mistake, pronounce, repeat, and means.	0.8	0.601

Complexity5 metrics

Metric	1	2
Avg Sentence Length i What it shows: How long the student's speaking sentences are on average. How we measure it: Mean alphabetic token count per detected speaking sentence, recomputed over the lesson from speaking-only sentences.	9.136	10.607
Sentences 10+ Words i What it shows: How many student sentences are at least ten words long. How we measure it: Count of detected student sentences whose alphabetic token count is 10 or more, summed across the lesson.	172	176
Complex Words (6+ chars) i What it shows: How often the student uses longer, more information-dense word forms while speaking. How we measure it: Count of speaking alpha tokens with 6 or more characters after deterministic cleanup and repeat collapsing.	963	763
Long Words (8+ chars %) i What it shows: The share of speaking words that are especially long. How we measure it: 100 times speaking alpha tokens with 8 or more characters divided by all speaking alpha tokens.	8.563	6.24
Complex Sentence Rate (%) i What it shows: How often the student uses speaking sentences with linking or subordinating structure. How we measure it: Percentage of speaking sentences containing connector markers such as because, although, while, if, when, which, but, so, therefore, or since.	32.112	42.963

Lexical range1 metric

Metric	1	2
MATTR-50 i What it shows: Vocabulary variety in the student's speaking turns, with less distortion from lesson length than a simple unique-word ratio. How we measure it: Moving-average type-token ratio over 50-word windows from speaking tokens only; if there are fewer than 50 speaking words, we fall back to unique tokens divided by total tokens.	0.71	0.668

Engagement signal1 metric

Metric	1	2
Elaboration Depth i What it shows: How much detail the student gives after open tutor prompts when responding in speaking mode. How we measure it: Average speaking-response length in words after tutor prompts such as why, how, tell me, or describe.	8.643	3.862

Reading activity5 metrics

Metric	1	2
Reading Turns i What it shows: How many student turns in the lesson were classified as reading aloud rather than free speaking. How we measure it: Count of student dialogue turns labeled as reading after the reading-vs-speaking classifier runs on the lesson transcript.	0	0
Reading Alpha Tokens i What it shows: How much student word volume came from reading aloud. How we measure it: Count of alphabetic student tokens assigned to reading turns after repeat collapsing.	0	0
Reading Duration (s) i What it shows: How much lesson time the student spent reading aloud. How we measure it: Sum of durations for student turns labeled as reading.	0	0
Reading WPM i What it shows: How fast the student read aloud during reading turns. How we measure it: Reading alpha-token count divided by reading-turn minutes. This is tracked separately from speaking WPM and does not affect the Progress Index.	0	0
Reading Share (%) i What it shows: What share of the student's total word volume came from reading aloud. How we measure it: 100 times reading alpha tokens divided by all student alpha tokens from both speaking and reading turns.	0	0

Standalone recordings

Audio Transcript Analysis

Full lessons use the five-rubric Progress Index (with Engagement). Single-speaker recordings don't have a tutor, so we swap Engagement for Naturalness and drop the tutor-side signals we can't observe — giving each clip a comparable 0–100 snapshot.

Native Avg Snapshot91.8

4 recordings

Non-Native Avg Snapshot78.2

5 recordings

Native Advantage+13.6

Mean native minus mean non-native

How we score single-speaker audio Audio Snapshot formula, in plain English

Audio Snapshot = 0.20 · Fluency + 0.25 · Accuracy + 0.15 · Complexity + 0.15 · Lexical Range + 0.25 · Naturalness

The five ingredients

Each ingredient is a 0–100 score. The snapshot is a weighted average.

Fluency 20%

How smoothly they speak — pacing, pauses, fillers.
Accuracy 25%

Tier-weighted grammar mistakes from the transcript.
Complexity 15%

Sentence length and use of connectors.
Lexical Range 15%

Vocabulary variety (MATTR-50).
Naturalness 25%

Does it sound like a native would say it? Replaces Engagement here.

Why Naturalness replaces Engagement

Full lessons measure Engagement from tutor–student interaction (talk ratio, latency, elaboration, tutor corrections). Single-speaker recordings have no tutor, so those signals are missing.

Lessons use Engagement Needs tutor side

Audio uses Naturalness Transcript-only signal

How the Naturalness score is built

Start at 100. Scan the transcript for phrasing a native speaker would word differently. Add up penalties, normalize per 100 spoken words, convert to a 0–100 score. Fewer issues = higher score.

Awkward phrase / collocation ×3.0

“applied with my team” “winning of the hackathon”

Off word choice ×2.5

“higher energy” “scientific fair”

Article / preposition ×2.0

“on the weekend” “the homework”

Sentence linking ×1.0

“so because that” “and then and”

We also add a small ×1.5 penalty for explicit lexical-uncertainty cues such as “the English word, I don't know…”.

Weighted issue rate rate = (3.0·phrase + 2.5·word_choice + 2.0·article_prep + 1.0·linking) ÷ speaking_tokens × 100 → Naturalness = clamp(100 − scaled(rate), 0, 100)

What's intentionally left out

Not scored

Accent & pronunciation. Naturalness is transcript-only; it doesn't judge how the words sounded.

Not available

Tutor-side signals (speaking share, response latency, elaboration depth, tutor correction rate) can't be observed in a solo recording, so we omit them rather than guess.

Single-speaker transcript estimate

Student 1

non-native

Estimated Progress Snapshot 83.5

Metric detail

Available Metrics

Speaking Alpha Tokens	127
Speaking Duration (s)	56.06
Student WPM	135.926
MATTR-50	0.791
Avg Sentence Length	11.545
Complex Sentence Rate (%)	18.182
Long Words (8+ chars %)	10.236
Long Pauses >1s	2
Filler Ratio (%)	0
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	1
Naturalness Issues: Phrase	0
Naturalness Issues: Word Choice	1
Naturalness Issues: Article/Prep	0
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	1.181
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 2

native

Estimated Progress Snapshot 93.0

Metric detail

Available Metrics

Speaking Alpha Tokens	174
Speaking Duration (s)	53.64
Student WPM	194.631
MATTR-50	0.825
Avg Sentence Length	10.875
Complex Sentence Rate (%)	37.5
Long Words (8+ chars %)	9.195
Long Pauses >1s	1
Filler Ratio (%)	0
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	0
Naturalness Issues: Phrase	0
Naturalness Issues: Word Choice	0
Naturalness Issues: Article/Prep	0
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	0
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 3

native

Estimated Progress Snapshot 89.9

Metric detail

Available Metrics

Speaking Alpha Tokens	116
Speaking Duration (s)	53.56
Student WPM	129.948
MATTR-50	0.863
Avg Sentence Length	10.545
Complex Sentence Rate (%)	0
Long Words (8+ chars %)	17.241
Long Pauses >1s	1
Filler Ratio (%)	0
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	0
Naturalness Issues: Phrase	0
Naturalness Issues: Word Choice	0
Naturalness Issues: Article/Prep	0
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	0
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 4

non-native

Estimated Progress Snapshot 71.7

Metric detail

Available Metrics

Speaking Alpha Tokens	111
Speaking Duration (s)	63.28
Student WPM	105.247
MATTR-50	0.666
Avg Sentence Length	13.875
Complex Sentence Rate (%)	25
Long Words (8+ chars %)	11.712
Long Pauses >1s	1
Filler Ratio (%)	1.802
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	3
Naturalness Issues: Phrase	0
Naturalness Issues: Word Choice	2
Naturalness Issues: Article/Prep	0
Naturalness Issues: Linking	1
Weighted Naturalness Issue Rate (per 100w)	5.405
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 5

non-native

Estimated Progress Snapshot 83.8

Metric detail

Available Metrics

Speaking Alpha Tokens	128
Speaking Duration (s)	50.78
Student WPM	151.241
MATTR-50	0.801
Avg Sentence Length	11.636
Complex Sentence Rate (%)	54.545
Long Words (8+ chars %)	10.156
Long Pauses >1s	0
Filler Ratio (%)	1.562
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	2
Naturalness Issues: Phrase	1
Naturalness Issues: Word Choice	1
Naturalness Issues: Article/Prep	0
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	4.297
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 6

non-native

Estimated Progress Snapshot 73.1

Metric detail

Available Metrics

Speaking Alpha Tokens	129
Speaking Duration (s)	56.92
Student WPM	135.98
MATTR-50	0.773
Avg Sentence Length	12.9
Complex Sentence Rate (%)	40
Long Words (8+ chars %)	8.527
Long Pauses >1s	1
Filler Ratio (%)	0.775
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	6
Naturalness Issues: Phrase	4
Naturalness Issues: Word Choice	1
Naturalness Issues: Article/Prep	1
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	12.791
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 7

native

Estimated Progress Snapshot 95.1

Metric detail

Available Metrics

Speaking Alpha Tokens	208
Speaking Duration (s)	58.4
Student WPM	213.699
MATTR-50	0.841
Avg Sentence Length	10.947
Complex Sentence Rate (%)	36.842
Long Words (8+ chars %)	12.5
Long Pauses >1s	0
Filler Ratio (%)	0.481
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	0
Naturalness Issues: Phrase	0
Naturalness Issues: Word Choice	0
Naturalness Issues: Article/Prep	0
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	0
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 8

non-native

Estimated Progress Snapshot 78.8

Metric detail

Available Metrics

Speaking Alpha Tokens	153
Speaking Duration (s)	60.08
Student WPM	152.796
MATTR-50	0.689
Avg Sentence Length	11.769
Complex Sentence Rate (%)	46.154
Long Words (8+ chars %)	3.268
Long Pauses >1s	0
Filler Ratio (%)	0.654
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	2
Naturalness Issues: Phrase	1
Naturalness Issues: Word Choice	0
Naturalness Issues: Article/Prep	1
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	3.268
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Single-speaker transcript estimate

Student 9

native

Estimated Progress Snapshot 89.1

Metric detail

Available Metrics

Speaking Alpha Tokens	178
Speaking Duration (s)	62.11
Student WPM	171.953
MATTR-50	0.765
Avg Sentence Length	8.476
Complex Sentence Rate (%)	19.048
Long Words (8+ chars %)	10.674
Long Pauses >1s	1
Filler Ratio (%)	0
Mistakes (total)	0
Mistakes T1 (Core)	0
Mistakes T2 (Intermediate)	0
Mistakes T3 (Stretch)	0
Weighted Error Rate (per 100w)	0
Naturalness Issues (total)	0
Naturalness Issues: Phrase	0
Naturalness Issues: Word Choice	0
Naturalness Issues: Article/Prep	0
Naturalness Issues: Linking	0
Weighted Naturalness Issue Rate (per 100w)	0
Reading Turns	0
Reading WPM	0
Reading Share (%)	0

Exact Scoring Formulas (Reference)

Fluency = 0.40*wpm + 0.30*inverse_disfluency + 0.30*inverse_long_pause_rate
Accuracy = log-mapped tier-weighted mistake rate
Complexity = 0.40*avg_sentence_len + 0.35*complex_sentence_rate + 0.25*long_words_pct
Lexical Range = MATTR-50
Engagement = 0.50*asr_confidence + 0.25*speaking_share + 0.15*elaboration_depth + 0.10*inverse_response_latency

student_response_latency_s = median gap between a tutor turn ending and the next student turn beginning
elaboration_depth = average student response length after open tutor prompts like why, how, tell me, or describe
tutor_correction_rate = supplementary context only; it does not affect the Progress Index

student_reading_wpm = reading alpha tokens divided by reading-turn minutes
student_reading_share_pct = share of the student's total alpha tokens that came from reading turns

subscore_fluency × 0.25
subscore_accuracy × 0.25
subscore_complexity × 0.20
subscore_lexical_range × 0.15
subscore_engagement × 0.15

Audio transcript snapshots below use a separate audio-only formula: they keep the lesson anchors for Fluency, Accuracy, Complexity, and Lexical Range, but replace Engagement with Naturalness.

Discover the
formula for
progress.

How we score progress.

Results

Progress Trend

Subscore Trend

Lesson Breakdown

1

2

3

Sound More Native

Lesson Metrics

Progress Trend

Subscore Trend

Lesson Breakdown

1

2

Sound More Native

Lesson Metrics

Audio Transcript Analysis

The five ingredients

Why Naturalness replaces Engagement

How the Naturalness score is built

What's intentionally left out

Student 1

Student 2

Student 3

Student 4

Student 5

Student 6

Student 7

Student 8

Student 9

Discover theformula forprogress.

How we score progress.

Results

Progress Trend

Subscore Trend

Lesson Breakdown

1

2

3

Sound More Native

Lesson Metrics

Progress Trend

Subscore Trend

Lesson Breakdown

1

2

Sound More Native

Lesson Metrics

The five ingredients

Why Naturalness replaces Engagement

How the Naturalness score is built

What's intentionally left out

Student 1

Student 2

Student 3

Student 4

Student 5

Student 6

Student 7

Student 8

Student 9

Discover the
formula for
progress.