accuracy benchmark
Artificial Analysis Speech To Text Leaderboard
Direct model-level leaderboard results from Artificial Analysis.
Updated Aug 18, 2026
Models55
Model coverage55
Metricaa_wer_index
EvidenceA
Artificial Analysis Speech To Text Ranking
Lower aa_wer_index ranks better on this benchmark.
Sort by
Rank | Model | aa_wer_index | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank02 | ModelSPSpeechmatics EnhancedSpeechmatics | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank03 | ModelMA | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank04 | ModelGLSolaria-1Gladia | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank05 | ModelSMSmallest AI Pulse ProSmallest.ai | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank06 | ModelGO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank07 | ModelAM Nova 2 ProAmazon | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank08 | ModelST | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank09 | ModelOP | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank10 | ModelOP | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank11 | ModelGO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank12 | ModelAL | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank13 | ModelGO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank14 | ModelOP | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank15 | ModelAS | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank16 | ModelGO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank17 | ModelGO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank18 | ModelAL | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank19 | ModelMI | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank20 | ModelSOSoniox V4Soniox | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank21 | ModelGO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank22 | ModelGO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank23 | ModelMA | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank24 | ModelEL | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank25 | ModelAS | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank26 | ModelOP | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank27 | ModelCO | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank28 | ModelSMSmallest AI PulseSmallest.ai | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank29 | ModelMI | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank30 | ModelMOModulate STT Batch English VFastModulate | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank31 | ModelMI | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank32 | ModelAS | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank33 | ModelXA | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank34 | ModelSPMeliaSpeechmatics | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank35 | ModelREResonant-1Reson8 | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank36 | ModelNV | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank37 | ModelGLSolaria-3Gladia | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank38 | ModelAMAmazon TranscribeAmazon | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank39 | ModelI(Inkling (256K) | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank40 | ModelSOSoniox v5 AsyncSoniox | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank41 | ModelOP | aa_wer_index0 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank42 | ModelGO | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank43 | ModelAMNova 2 OmniAmazon | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank44 | ModelGO | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank45 | ModelSPSpeechmatics StandardSpeechmatics | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank46 | ModelNV | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank47 | ModelNV | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank48 | ModelGO | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank49 | ModelGRGradium Speech-to-TextGradium | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank50 | ModelDE | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank51 | ModelAL | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank52 | ModelGO | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank53 | ModelRARev AIRev AI | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank54 | ModelAL | aa_wer_index0.1 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
| Rank55 | ModelGO | aa_wer_index0.3 index | PercentileN/A | Participants55 | EvidenceA | Evaluated |
Artificial Analysis Speech To Text Highlights
The leading models and scores on this benchmark.
Artificial Analysis Speech To Text Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Artificial Analysis Speech To Text
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis artificial analysis speech to text AI model leaderboard uses ascending aa_wer_index in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01OPGPT-4o Mini TranscribeOpenAI
- aa_wer_index
- 0 index
Strengths
- Ranks #1 of 55 compared models
- A evidence result
Considerations
- This result measures Artificial Analysis Speech To Text, not total model capability
- 02SPSpeechmatics EnhancedSpeechmatics
- aa_wer_index
- 0 index
Strengths
- Ranks #2 of 55 compared models
- A evidence result
Considerations
- This result measures Artificial Analysis Speech To Text, not total model capability
- 03MAVoxtral SmallMistral AI
- aa_wer_index
- 0 index
Strengths
- Ranks #3 of 55 compared models
- A evidence result
Considerations
- This result measures Artificial Analysis Speech To Text, not total model capability
- 04GLSolaria-1Gladia
- aa_wer_index
- 0 index
Strengths
- Ranks #4 of 55 compared models
- A evidence result
Considerations
- This result measures Artificial Analysis Speech To Text, not total model capability
- 05SMSmallest AI Pulse ProSmallest.ai
- aa_wer_index
- 0 index
Strengths
- Ranks #5 of 55 compared models
- A evidence result
Considerations
- This result measures Artificial Analysis Speech To Text, not total model capability
Selection summary
Best AI Models for Artificial Analysis Speech To Text
GPT-4o Mini Transcribe currently leads Artificial Analysis Speech To Text with 0 index. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is Artificial Analysis Speech To Text?
What Artificial Analysis Speech To Text measures and how its scores work.
Direct model-level leaderboard results from Artificial Analysis.
Scores are shown in index. This benchmark is verified and has an evidence level of A.
- Family
- Artificial Analysis speech-to-text
- Modality
- audio
- Primary category
- accuracy
- Score direction
- lower
- LLMBoard eligible
- Yes
- Evaluation key
- aa-speech-to-text|artificial-analysis|current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Artificial Analysis Speech To Text.
Which model scores highest on Artificial Analysis Speech To Text?
GPT-4o Mini Transcribe is currently ranked first with 0 index.
What does Artificial Analysis Speech To Text measure?
Direct model-level leaderboard results from Artificial Analysis.
Is a higher aa_wer_index better?
No. Lower values rank better for this benchmark.
How many models are compared?
55 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.