llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

speech to text benchmark

CoVoST2 Leaderboard

CoVoST 2 is a large-scale multilingual speech translation corpus derived from Common Voice, covering translations from 21 languages into English and from English into 15 languages. The dataset contains 2,880 hours of speech with 78K speakers for speech translation research.

Updated Aug 17, 2026

Models4
Model coverage4
MetricScore
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

CoVoST2 Ranking

Higher score ranks better on this benchmark.

4 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelAMNova 2 OmniAmazonScore40.7%Percentile100.0%Participants4EvidenceCEvaluatedAug 17, 2026
Rank02ModelGOGemini 2.0 FlashGoogleScore39.2%Percentile66.7%Participants4EvidenceCEvaluatedAug 17, 2026
Rank03ModelGOGemma 4 12BGoogleScore38.5%Percentile33.3%Participants4EvidenceCEvaluatedAug 17, 2026
Rank04ModelGOGemini 2.0 Flash-LiteGoogleScore38.4%Percentile0.0%Participants4EvidenceCEvaluatedAug 17, 2026

CoVoST2 Highlights

The leading models and scores on this benchmark.

Rank #1Nova 2 Omni40.7%Rank #2Gemini 2.0 Flash39.2%Rank #3Gemma 4 12B38.5%Rank #4Gemini 2.0 Flash-Lite38.4%

CoVoST2 Score Distribution

A closer view of the leading scores on this benchmark.

CoVoST2

The Top AI Models for CoVoST2

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

Ranking basisThis covost2 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    AM
    Nova 2 OmniAmazon
    Score
    40.7%

    Strengths

    • Ranks #1 of 4 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CoVoST2, not total model capability
  2. 02
    GO
    Gemini 2.0 FlashGoogle
    Score
    39.2%
    Speed
    Up to 183 tok/s via Google

    Strengths

    • Ranks #2 of 4 compared models
    • 67th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CoVoST2, not total model capability
  3. 03
    GO
    Gemma 4 12BGoogle
    Score
    38.5%

    Strengths

    • Ranks #3 of 4 compared models
    • 33th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CoVoST2, not total model capability
  4. 04
    GO
    Gemini 2.0 Flash-LiteGoogle
    Score
    38.4%
    Speed
    Up to 85 tok/s via Google

    Strengths

    • Ranks #4 of 4 compared models
    • 0th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CoVoST2, not total model capability

Selection summary

Best AI Models for CoVoST2

Nova 2 Omni currently leads CoVoST2 with 40.7%. 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.

Benchmark rank #1Nova 2 Omni40.7%Benchmark rank #2Gemini 2.0 Flash39.2% · Up to 183 tok/s via GoogleBenchmark rank #3Gemma 4 12B38.5%

What is CoVoST2?

What CoVoST2 measures and how its scores work.

CoVoST 2 is a large-scale multilingual speech translation corpus derived from Common Voice, covering translations from 21 languages into English and from English into 15 languages. The dataset contains 2,880 hours of speech with 78K speakers for speech translation research.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
CoVoST2
Modality
audio
Primary category
speech to text
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
covost2|llm-stats-current

Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about CoVoST2.

Which model scores highest on CoVoST2?

Nova 2 Omni is currently ranked first with 40.7%.

What does CoVoST2 measure?

CoVoST 2 is a large-scale multilingual speech translation corpus derived from Common Voice, covering translations from 21 languages into English and from English into 15 languages. The dataset contains 2,880 hours of speech with 78K speakers for speech translation research.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

4 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.