PazaBench v2
Version 2
Models transcribe speech in 61 African languages. The leaderboard measures character error rate, word error rate and transcription speed.
Microsoft compares 53 models on 417,460 samples across 93 evaluation splits. The release adds four dataset groups.
- Made by
- Microsoft Research Africa, Nairobi
- Released
- July 2026
- Kind
- Speech recognition and translation
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Many languages
- Interaction
- Single turn
- Items from
- Another benchmark
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- PazaBench
- In views
- Audio and speech, Many languages
- Last model added
- February 2025
- Scores refreshed
- November 20th, 2026
facebook/omniASR-LLM-7B-ZS tops the leaderboard with 15.6% Whisper large-v3-turbo leads with 73.3% among models released by February 2025
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 Whisper large-v3-turbo, at 73.3%. This view shows only models we track, each at its best.
The newest model with a score here came out in February 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 facebook/omniASR-LLM-7B-ZS 15.6%
- 2 facebook/omniASR-LLM-7B 16.1%
- 3 facebook/omniASR-LLM-3B 18.3%
- 4 facebook/omniASR-LLM-1B 19%
- 5 facebook/omniASR-CTC-7B 19.2%
- 6 facebook/omniASR-LLM-300M 19.3%
- 7 facebook/omniASR-CTC-3B 20.2%
- 8 facebook/omniASR-CTC-1B 20.6%
- 9 facebook/omniASR-CTC-300M 22.5%
- 10 facebook/mms-1b-all 30.1%
- 11 paza/microsoft-paza-mms-1b-all 33.9%
- 12 facebook/mms-1b-fl102 35.9%
- 13 facebook/wav2vec2-conformer-rel-pos-large-960h-ft 48.6%
- 14 facebook/hubert-large-ls960-ft 48.7%
- 15 facebook/hubert-xlarge-ls960-ft 49.3%
- 16 facebook/wav2vec2-large-960h-lv60-self 49.7%
- 17 paza/microsoft-paza-Phi-4-multimodal-instruct 51.6%
- 18 facebook/wav2vec2-large-robust-ft-libri-960h 52%
- 19 nvidia/parakeet-tdt-0.6b-v3 52.7%
- 20 facebook/data2vec-audio-large-960h 57%
- 21 facebook/wav2vec2-conformer-rope-large-960h-ft 57.9%
- 22 facebook/data2vec-audio-base-960h 60.6%
- 23 facebook/wav2vec2-large-960h 60.8%
- 24 paza/microsoft-paza-whisper-large-v3-turbo 63%
- 25 facebook/wav2vec2-base-960h 64.9%
- 26 nvidia/canary-qwen-2.5b 66.8%
- 27 openai/whisper-small.en 69.9%
- 28 openai/whisper-medium.en 70.4%
- 29 nvidia/canary-1b-v2 71%
- 30 Whisper large-v3-turbo 73.3%
- 31 openai/whisper-base.en 73.3%
- 32
Phi-4-multimodal 74.2%
- 33 efficient/speech-lite-whisper-large-v3-turbo-acc 74.3%
- 34 distil/whisper-distil-large-v3 74.3%
- 35 openai/whisper-large 75.9%
- 36 openai/whisper-tiny.en 76.2%
- 37 openai/whisper-large-v2 77.3%
- 38 distil/whisper-distil-medium.en 78.5%
- 39 kyutai/stt-2.6b-en 78.8%
- 40 distil/whisper-distil-large-v2 79.3%
- 41 Whisper large-v3 79.4%
- 42 efficient/speech-lite-whisper-large-v3-acc 80.3%
- 43 efficient/speech-lite-whisper-large-v3 82.4%
- 44 efficient/speech-lite-whisper-large-v3-turbo 82.8%
- 45 efficient/speech-lite-whisper-large-v3-fast 84.5%
- 46 efficient/speech-lite-whisper-large-v3-turbo-fast 89.9%
- 47 facebook/seamless-m4t-v2-large 92%
- 48 usefulsensors/moonshine-base 99.98%
- 49
Qwen2-Audio-7B-Instruct 135%
- 50 usefulsensors/moonshine-tiny 155.8%
- 51 ibm/granite-granite-speech-3.3-2b 292.8%
- 52 ibm/granite-granite-speech-3.3-8b 360.6%
- 53 Qwen/Qwen2-Audio-7B 501.3%
Source: Official PazaBench v2 leaderboard
- 1 Whisper large-v3-turbo 73.3%
- 2
Phi-4-multimodal 74.2%
- 3 Whisper large-v3 79.4%
- 4
Qwen2-Audio-7B-Instruct 135%
Source: Official PazaBench v2 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | facebook/omniASR-LLM-7B-ZS | 15.6% | Official leaderboard | ||
| 2 | facebook/omniASR-LLM-7B | 16.1% | Official leaderboard | ||
| 3 | facebook/omniASR-LLM-3B | 18.3% | Official leaderboard | ||
| 4 | facebook/omniASR-LLM-1B | 19% | Official leaderboard | ||
| 5 | facebook/omniASR-CTC-7B | 19.2% | Official leaderboard | ||
| 6 | facebook/omniASR-LLM-300M | 19.3% | Official leaderboard | ||
| 7 | facebook/omniASR-CTC-3B | 20.2% | Official leaderboard | ||
| 8 | facebook/omniASR-CTC-1B | 20.6% | Official leaderboard | ||
| 9 | facebook/omniASR-CTC-300M | 22.5% | Official leaderboard | ||
| 10 | facebook/mms-1b-all | 30.1% | Official leaderboard | ||
| 11 | paza/microsoft-paza-mms-1b-all | 33.9% | Official leaderboard | ||
| 12 | facebook/mms-1b-fl102 | 35.9% | Official leaderboard | ||
| 13 | facebook/wav2vec2-conformer-rel-pos-large-960h-ft | 48.6% | Official leaderboard | ||
| 14 | facebook/hubert-large-ls960-ft | 48.7% | Official leaderboard | ||
| 15 | facebook/hubert-xlarge-ls960-ft | 49.3% | Official leaderboard | ||
| 16 | facebook/wav2vec2-large-960h-lv60-self | 49.7% | Official leaderboard | ||
| 17 | paza/microsoft-paza-Phi-4-multimodal-instruct | 51.6% | Official leaderboard | ||
| 18 | facebook/wav2vec2-large-robust-ft-libri-960h | 52% | Official leaderboard | ||
| 19 | nvidia/parakeet-tdt-0.6b-v3 | 52.7% | Official leaderboard | ||
| 20 | facebook/data2vec-audio-large-960h | 57% | Official leaderboard | ||
| 21 | facebook/wav2vec2-conformer-rope-large-960h-ft | 57.9% | Official leaderboard | ||
| 22 | facebook/data2vec-audio-base-960h | 60.6% | Official leaderboard | ||
| 23 | facebook/wav2vec2-large-960h | 60.8% | Official leaderboard | ||
| 24 | paza/microsoft-paza-whisper-large-v3-turbo | 63% | Official leaderboard | ||
| 25 | facebook/wav2vec2-base-960h | 64.9% | Official leaderboard | ||
| 26 | nvidia/canary-qwen-2.5b | 66.8% | Official leaderboard | ||
| 27 | openai/whisper-small.en | 69.9% | Official leaderboard | ||
| 28 | openai/whisper-medium.en | 70.4% | Official leaderboard | ||
| 29 | nvidia/canary-1b-v2 | 71% | Official leaderboard | ||
| 30 | Whisper large-v3-turbo | 73.3% | Oct 2024 | Official leaderboard | |
| 31 | openai/whisper-base.en | 73.3% | Official leaderboard | ||
| 32 | | 74.2% | Feb 2025 | Official leaderboard | |
| 33 | efficient/speech-lite-whisper-large-v3-turbo-acc | 74.3% | Official leaderboard | ||
| 34 | distil/whisper-distil-large-v3 | 74.3% | Official leaderboard | ||
| 35 | openai/whisper-large | 75.9% | Official leaderboard | ||
| 36 | openai/whisper-tiny.en | 76.2% | Official leaderboard | ||
| 37 | openai/whisper-large-v2 | 77.3% | Official leaderboard | ||
| 38 | distil/whisper-distil-medium.en | 78.5% | Official leaderboard | ||
| 39 | kyutai/stt-2.6b-en | 78.8% | Official leaderboard | ||
| 40 | distil/whisper-distil-large-v2 | 79.3% | Official leaderboard | ||
| 41 | Whisper large-v3 | 79.4% | Nov 2023 | Official leaderboard | |
| 42 | efficient/speech-lite-whisper-large-v3-acc | 80.3% | Official leaderboard | ||
| 43 | efficient/speech-lite-whisper-large-v3 | 82.4% | Official leaderboard | ||
| 44 | efficient/speech-lite-whisper-large-v3-turbo | 82.8% | Official leaderboard | ||
| 45 | efficient/speech-lite-whisper-large-v3-fast | 84.5% | Official leaderboard | ||
| 46 | efficient/speech-lite-whisper-large-v3-turbo-fast | 89.9% | Official leaderboard | ||
| 47 | facebook/seamless-m4t-v2-large | 92% | Official leaderboard | ||
| 48 | usefulsensors/moonshine-base | 99.98% | Official leaderboard | ||
| 49 | | 135% | Aug 2024 | Official leaderboard | |
| 50 | usefulsensors/moonshine-tiny | 155.8% | Official leaderboard | ||
| 51 | ibm/granite-granite-speech-3.3-2b | 292.8% | Official leaderboard | ||
| 52 | ibm/granite-granite-speech-3.3-8b | 360.6% | Official leaderboard | ||
| 53 | Qwen/Qwen2-Audio-7B | 501.3% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Whisper large-v3-turbo | 73.3% | Oct 2024 | Official leaderboard | |
| 2 | | 74.2% | Feb 2025 | Official leaderboard | |
| 3 | Whisper large-v3 | 79.4% | Nov 2023 | Official leaderboard | |
| 4 | | 135% | Aug 2024 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Word error rate and Inverse real-time factor. Each ranks models on one part of the test. Whisper large-v3-turbo leads both. Arrows show how far a model moved from its overall rank among the models we track.
Word error rate
4 models we track have a score here.
- 1 Whisper large-v3-turbo 96.7%
- 2 Whisper large-v3 ↑1 98.1%
- 3
Phi-4-multimodal ↓1 112.8%
- 4
Qwen2-Audio-7B-Instruct 160%
Inverse real-time factor
4 models we track have a score here.
- 1 Whisper large-v3-turbo 181.5×
- 2
Qwen2-Audio-7B-Instruct ↑2 70.5×
- 3 Whisper large-v3 62.7×
- 4
Phi-4-multimodal ↓2 16.3×
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official PazaBench v2 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PazaBench v2 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.
Versions
More 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 21 months ago, in February 2025, for Phi-4-multimodal. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (53 entries).
- Pass Models scored 4 models we track, plus 49 other entries on its leaderboard.
- Warning Newest score The newest came 21 months ago, in February 2025, for Phi-4-multimodal.
- 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 huggingface.co: 4 rows for models we track and 49 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.