Benchmark Almanac

Addis Scribe Benchmark

Addis Scribe Afaan Oromo 21.1% tops its leaderboard Gemini 4 Argon 29.9% leads the models we track
Not in model cards

Speech models transcribe recordings in seven African languages. Addis AI compares transcripts with human references and measures how quickly some systems return text.

Addis AI compares eight systems on the same 150 Afaan Oromo clips from 23 speakers. Its eleven result rows include multiple operating modes.

Made by
Addis AI
Released
October 2026
Kind
Speech recognition and translation
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Many languages
In and out
Audio → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 4 Argon #10 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
8
Entries on its own leaderboard, 1 model we track

Addis Scribe Afaan Oromo tops the leaderboard with 21.1% Gemini 4 Argon leads with 29.9%

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 4 Argon, at 29.9%. This view shows only models we track, each at its best.

  1. 1 Addis Scribe Afaan Oromo live, 1.12 s chunks 21.1%
  2. 2 Ethio-ASR Oromo offline 24.8%
  3. 3 Ethio-ASR multilingual 600M offline 25.7%
  4. 4 WAXAL benchmark Whisper-small Oromo offline 28.2%
  5. 5 WAXAL benchmark MMS-300M Oromo offline 29.5%
  6. 6 Google Gemini Flash (latest) whole file 29.8%
  7. 7 Gemini 4 Argon whole file 29.9%
  8. 8 Google Chirp 2 (om-ET) batch 34.8%

Source: Official Addis Scribe Benchmark leaderboard

Source: Official Addis Scribe Benchmark leaderboard

#EntryScoreSettingDateSource
1 Addis Scribe Afaan Oromo 21.1% live, 1.12 s chunks Official leaderboard
2 Ethio-ASR Oromo 24.8% offline Official leaderboard
3 Ethio-ASR multilingual 600M 25.7% offline Official leaderboard
4 WAXAL benchmark Whisper-small Oromo 28.2% offline Official leaderboard
5 WAXAL benchmark MMS-300M Oromo 29.5% offline Official leaderboard
6 Google Gemini Flash (latest) 29.8% whole file Official leaderboard
7 Gemini 4 Argon 29.9% whole file Sep 2026 Official leaderboard
8 Google Chirp 2 (om-ET) 34.8% batch Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 4 Argon 29.9% whole file Sep 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% Gemini 4 Argon 0% 20% 40% 60% 80% 100% Gemini 4 Argon

Source: Official Addis Scribe Benchmark 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

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (8 entries).
  • Pass Models scored 1 model we track, plus 7 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
  • Note Frontier models Only 1 of the top 10 has a score. The strongest tested is Gemini 4 Argon (#10).
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on addisassistant.com: 1 row for models we track and 7 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