Benchmark Almanac

Voice Arena Dictation Bench

Aqua Voice 80.5% tops its leaderboard Gemini 3.5 Transcribe 75.8% leads the models we track
Not in model cards

Dictation tools turn speech into written drafts. Judges measure the share of drafts a user could send without edits.

The US English board covers 14 macOS dictation tools.

Made by
Voice Arena
Kind
Speech recognition and translation
Level
Everyday
Scored
Graded by a model
Answers
Short answer
Measures
Capability
Language
English
In and out
Audio → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Audio and speech
Last model added
August 2026
Scores refreshed
November 20th, 2026
14
Entries on its own leaderboard, 1 model we track

Aqua Voice tops the leaderboard with 80.5% Gemini 3.5 Transcribe leads with 75.8%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemini 3.5 Transcribe, at 75.8%. This view shows only models we track, each at its best.

  1. 1 Aqua Voice 80.5%
  2. 2 Wispr Flow 79.3%
  3. 3 Blurt 78%
  4. 4 Willow Voice 76.5%
  5. 5 Gemini 3.5 Transcribe 75.8%
  6. 6 Spokenly 73.8%
  7. 7 Granola 71.9%
  8. 8 Kivi 69.3%
  9. 9 Meta AI 69.3%
  10. 10 ChatGPT Dictation 64.3%
  11. 11 Claude Dictation 64%
  12. 12 Superwhisper 59.8%
  13. 13 Perplexity Dictation 52.7%
  14. 14 Apple Dictation 34.5%

Source: Official Voice Arena Dictation Bench leaderboard

Source: Official Voice Arena Dictation Bench leaderboard

#EntryScoreSettingDateSource
1 Aqua Voice 80.5% Official leaderboard
2 Wispr Flow 79.3% Official leaderboard
3 Blurt 78% Official leaderboard
4 Willow Voice 76.5% Official leaderboard
5 Gemini 3.5 Transcribe 75.8% Aug 2026 Official leaderboard
6 Spokenly 73.8% Official leaderboard
7 Granola 71.9% Official leaderboard
8 Kivi 69.3% Official leaderboard
9 Meta AI 69.3% Official leaderboard
10 ChatGPT Dictation 64.3% Official leaderboard
11 Claude Dictation 64% Official leaderboard
12 Superwhisper 59.8% Official leaderboard
13 Perplexity Dictation 52.7% Official leaderboard
14 Apple Dictation 34.5% Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3.5 Transcribe 75.8% Aug 2026 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Gemini 3.5 Transcribe 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Gemini 3.5 Transcribe

Source: Official Voice Arena Dictation Bench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (14 entries).
  • Pass Models scored 1 model we track, plus 13 other entries on its leaderboard.
  • Pass Newest score The newest is from August 2026, for Gemini 3.5 Transcribe.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 75.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on voicearena.com: 1 row for models we track and 13 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check