accuracy benchmark
Artificial Analysis Speech To Text is an accuracy benchmark based on the official AA WER Index leaderboard published by Artificial Analysis.
Updated Sep 8, 2026
Lower aa wer index ranks better on this benchmark.
Rank | Model | AA WER Index | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | AA WER Index0.00 index | Percentile100.00% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank02 | ModelSPSpeechmatics EnhancedSpeechmatics | AA WER Index0.00 index | Percentile98.25% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank03 | ModelMA | AA WER Index0.00 index | Percentile96.49% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank04 | ModelGLSolaria-1Gladia | AA WER Index0.00 index | Percentile94.74% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank05 | ModelSMSmallest AI Pulse ProSmallest.ai | AA WER Index0.00 index | Percentile92.98% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank06 | ModelGO | AA WER Index0.00 index | Percentile91.23% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank07 | ModelAM | AA WER Index0.00 index | Percentile89.47% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank08 | ModelST | AA WER Index0.00 index | Percentile87.72% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank09 | ModelOP | AA WER Index0.00 index | Percentile85.96% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank10 | ModelOP | AA WER Index0.00 index | Percentile84.21% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank11 | ModelGO | AA WER Index0.00 index | Percentile82.46% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank12 | ModelGO | AA WER Index0.00 index | Percentile80.70% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank13 | ModelAL | AA WER Index0.00 index | Percentile78.95% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank14 | ModelIN | AA WER Index0.00 index | Percentile77.19% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank15 | ModelMI | AA WER Index0.00 index | Percentile75.44% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank16 | ModelGO | AA WER Index0.00 index | Percentile73.68% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank17 | ModelOP | AA WER Index0.00 index | Percentile71.93% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank18 | ModelAS | AA WER Index0.00 index | Percentile70.18% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank19 | ModelGO | AA WER Index0.00 index | Percentile68.42% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank20 | ModelAL | AA WER Index0.00 index | Percentile66.67% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank21 | ModelSOSoniox V4Soniox | AA WER Index0.00 index | Percentile64.91% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank22 | ModelGO | AA WER Index0.00 index | Percentile63.16% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank23 | ModelGO | AA WER Index0.00 index | Percentile61.40% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank24 | ModelMA | AA WER Index0.00 index | Percentile59.65% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank25 | ModelEL | AA WER Index0.00 index | Percentile57.89% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank26 | ModelAS | AA WER Index0.00 index | Percentile56.14% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank27 | ModelOP | AA WER Index0.00 index | Percentile54.39% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank28 | ModelCO | AA WER Index0.00 index | Percentile52.63% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank29 | ModelSMSmallest AI PulseSmallest.ai | AA WER Index0.00 index | Percentile50.88% | Participants58 | EvidenceB | EvaluatedN/A |
| Rank30 | ModelMI | AA WER Index0.00 index | Percentile49.12% | Participants58 | EvidenceB | EvaluatedN/A |
The leading models and scores on this benchmark.
A closer view of the leading scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What Artificial Analysis Speech To Text measures and how its scores work.
Artificial Analysis Speech To Text is a benchmark for speech-to-text systems.
It reports the AA WER Index in index units.
Scores are shown in index. This benchmark is verified and has an evidence level of B.
Artificial Analysis. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about Artificial Analysis Speech To Text.
GPT-4o Mini Transcribe is currently ranked first with 0.00 index.
The current leaders are GPT-4o Mini Transcribe (0.00 index), Speechmatics Enhanced (0.00 index), and Voxtral Small (0.00 index).
No matched official input price is currently available.
No matched runtime record is currently available.
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
It reports the AA WER Index in index units.
No. Lower values rank better for this benchmark.
58 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.
Ranking basisThis artificial analysis speech to text AI model leaderboard uses ascending aa wer index in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
GPT-4o Mini Transcribe currently leads Artificial Analysis Speech To Text with 0.00 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.