llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeLeaderboardsSpeech-to-Text

Audio benchmarks

Speech-to-Text Leaderboard

Benchmark-specific speech recognition results. The current dataset does not define a cross-benchmark overall speech score.

Data as of 2026-08-07

On this page

  • Benchmarks
  • Highlights
  • FAQ

Published speech benchmarks

Each chart preserves its original metric and ranking direction.

Common Voice 15

View benchmark

CoVoST2

View benchmark

CoVoST2 en-zh

View benchmark

FLEURS

View benchmark

Speech benchmark leaders

Best on Common Voice 15Qwen2.5-Omni-7B0.076 pointsBest on CoVoST2Nova 2 Omni40.7%Best on CoVoST2 en-zhQwen2.5-Omni-7B0.414 pointsBest on FLEURSQwen2.5-Omni-7B95.9%

About speech rankings

What is the best speech-to-text model?

No single cross-benchmark winner is calculated. Use each benchmark leader above because the evaluations can use different datasets and metrics.

Why are there several charts?

The current registry preserves each speech benchmark's original metric and direction instead of combining unlike results.

How many speech benchmarks are published?

This page currently contains 4 published speech-to-text benchmark definitions.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai