Benchmark Almanac

Almieyar

Not in model cards

Models transcribe newly recorded speech in 17 Arabic dialects. The authors report word and character error rates across six dialect families.

Released
September 2026
Kind
Speech recognition and translation
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Measures
Capability
Language
Arabic
In and out
Audio → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
In views
Audio and speech
Last model added
March 2025
Scores refreshed
November 20th, 2026
12
Entries in its paper, 2 models we track

gpt-4o-transcribe leads with 34.9% gpt-4o-transcribe leads with 34.9%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. This view shows only models we track, each at its best.

  1. 1 gpt-4o-transcribe Zero-shot 34.9%
  2. 2 Voxtral-Mini-4B Zero-shot 41.1%
  3. 3 Fanar-STT-LF Zero-shot 45.9%
  4. 4 Whisper large-v3 Zero-shot 49.5%
  5. 5 SeamlessM4T-v2 Zero-shot 56.6%
  6. 6 Whisper-Medium Zero-shot 58.5%
  7. 7 Whisper-Small Zero-shot 69.7%
  8. 8 Moonshine-AR Zero-shot 71.7%
  9. 9 Wav2Vec2-53-AR Zero-shot 79.1%
  10. 10 Wav2Vec2-XLSR-AR Zero-shot 81.9%
  11. 11 Wav2Vec2-XLSR-v2 Zero-shot 84.8%
  12. 12 Sinai-STT Zero-shot 85.6%

Source: The Almieyar paper

Source: The Almieyar paper

#EntryScoreSettingDateSource
1 gpt-4o-transcribe 34.9% Zero-shot Mar 2025 Official leaderboard
2 Voxtral-Mini-4B 41.1% Zero-shot Official leaderboard
3 Fanar-STT-LF 45.9% Zero-shot Official leaderboard
4 Whisper large-v3 49.5% Zero-shot Nov 2023 Official leaderboard
5 SeamlessM4T-v2 56.6% Zero-shot Official leaderboard
6 Whisper-Medium 58.5% Zero-shot Official leaderboard
7 Whisper-Small 69.7% Zero-shot Official leaderboard
8 Moonshine-AR 71.7% Zero-shot Official leaderboard
9 Wav2Vec2-53-AR 79.1% Zero-shot Official leaderboard
10 Wav2Vec2-XLSR-AR 81.9% Zero-shot Official leaderboard
11 Wav2Vec2-XLSR-v2 84.8% Zero-shot Official leaderboard
12 Sinai-STT 85.6% Zero-shot Official leaderboard
#ModelScoreSettingDateSource
1 gpt-4o-transcribe 34.9% Zero-shot Mar 2025 Official leaderboard
2 Whisper large-v3 49.5% Zero-shot Nov 2023 Official leaderboard

Scores over time

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

In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 2025 gpt-4o-transcribe Whisper large-v3 0% 20% 40% 60% 80% 100% 2024 2025 gpt-4o-transcribe Whisper large-v3

Source: Official Almieyar 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

7 of 9 checks pass, 2 warnings. 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 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 2 models we track, plus 10 other entries on its leaderboard.
  • Warning Newest score The newest came 20 months ago, in March 2025, for gpt-4o-transcribe.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 rows for models we track and 10 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