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 Directory

Scoring & Data

Scoring & Data
1224 models729 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 Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

naturalness benchmark

TTS Arena V2 Leaderboard

TTS Arena V2 is an official text-to-speech human preference leaderboard published by TTS-AGI.

Updated Sep 8, 2026

Models17
Model coverage17
MetricBradley-Terry Elo
EvidenceB

On this page

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

TTS Arena V2 Ranking

Higher bradley-terry elo ranks better on this benchmark.

17 rows
Columns

Show columns

Sort by
Rank
Model
Bradley-Terry Elo
Percentile
Participants
Votes
Evidence
Evaluated
Rank01ModelINInworld TTS-1-MaxInworldBradley-Terry Elo1,557.00 eloPercentile100.00%Participants17Votes1,496EvidenceBEvaluatedN/A
Rank02ModelINInworld TTS-1InworldBradley-Terry Elo1,539.00 eloPercentile93.75%Participants17Votes1,976EvidenceBEvaluatedN/A
Rank03ModelSMLightning V3.1 Pro (Jul 2026)Smallest.aiBradley-Terry Elo1,536.00 eloPercentile87.50%Participants17Votes576EvidenceBEvaluatedN/A
Rank04ModelMISpeech 2.8 HDMiniMaxBradley-Terry Elo1,528.00 eloPercentile81.25%Participants17Votes536EvidenceBEvaluatedN/A
Rank05ModelHAOctave TTSHume AIBradley-Terry Elo1,523.00 eloPercentile75.00%Participants17Votes1,162EvidenceBEvaluatedN/A
Rank06ModelMISpeech 2.6 TurboMiniMaxBradley-Terry Elo1,521.00 eloPercentile68.75%Participants17Votes587EvidenceBEvaluatedN/A
Rank07ModelMISpeech 2.8 TurboMiniMaxBradley-Terry Elo1,520.00 eloPercentile62.50%Participants17Votes561EvidenceBEvaluatedN/A
Rank08ModelMISpeech 02 HDMiniMaxBradley-Terry Elo1,510.00 eloPercentile56.25%Participants17Votes1,254EvidenceBEvaluatedN/A
Rank09ModelMISpeech 2.6 HDMiniMaxBradley-Terry Elo1,508.00 eloPercentile50.00%Participants17Votes592EvidenceBEvaluatedN/A
Rank10ModelFAOpenAudio S1Fish AudioBradley-Terry Elo1,508.00 eloPercentile43.75%Participants17Votes571EvidenceBEvaluatedN/A
Rank11ModelELMultilingual V2ElevenLabsBradley-Terry Elo1,505.00 eloPercentile37.50%Participants17Votes1,156EvidenceBEvaluatedN/A
Rank12ModelELEleven Flash v2.5ElevenLabsBradley-Terry Elo1,505.00 eloPercentile31.25%Participants17Votes1,180EvidenceBEvaluatedN/A
Rank13ModelELEleven Turbo v2.5ElevenLabsBradley-Terry Elo1,505.00 eloPercentile25.00%Participants17Votes1,152EvidenceBEvaluatedN/A
Rank14ModelMISpeech 02 TurboMiniMaxBradley-Terry Elo1,503.00 eloPercentile18.75%Participants17Votes1,244EvidenceBEvaluatedN/A
Rank15ModelHISpeech 2.6HithinkBradley-Terry Elo1,502.00 eloPercentile12.50%Participants17Votes585EvidenceBEvaluatedN/A
Rank16ModelELEleven v3ElevenLabsBradley-Terry Elo1,498.00 eloPercentile6.25%Participants17Votes587EvidenceBEvaluatedN/A
Rank17ModelRAChatterboxResemble AIBradley-Terry Elo1,478.00 eloPercentile0.00%Participants17Votes1,793EvidenceBEvaluatedN/A

TTS Arena V2 Highlights

The leading models and scores on this benchmark.

TTS Arena V2 Score Distribution

A closer view of the leading scores on this benchmark.

TTS Arena V2

The Top AI Models for TTS Arena V2

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

What is TTS Arena V2?

What TTS Arena V2 measures and how its scores work.

TTS Arena V2 is a text-to-speech human preference leaderboard.

It measures naturalness using Bradley-Terry Elo, reported in elo.

Scores are shown in elo. This benchmark is verified and has an evidence level of B.

Family
TTS Arena V2
Modality
audio
Primary category
naturalness
Score direction
higher
LLMBoard eligible
No
Evaluation key
overall

TTS Arena V2. Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about TTS Arena V2.

Which model scores highest on TTS Arena V2?

Inworld TTS-1-Max is currently ranked first with 1,557.00 elo.

What are the top three models on TTS Arena V2?

The current leaders are Inworld TTS-1-Max (1,557.00 elo), Inworld TTS-1 (1,539.00 elo), and Lightning V3.1 Pro (Jul 2026) (1,536.00 elo).

Which TTS Arena V2 model has the lowest official input price?

No matched official input price is currently available.

Which models are fastest among TTS Arena V2 results?

No matched runtime record is currently available.

Does the highest bradley-terry elo result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does TTS Arena V2 measure?

It measures naturalness using Bradley-Terry Elo, reported in elo.

Is a higher bradley-terry elo better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

17 model results are currently shown.

Does this benchmark affect the overall score?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1Inworld TTS-1-Max1,557.00 elo
Rank #2Inworld TTS-11,539.00 elo
Rank #3Lightning V3.1 Pro (Jul 2026)1,536.00 elo
Rank #4Speech 2.8 HD1,528.00 elo

Ranking basisThis tts arena v2 AI model leaderboard uses descending bradley-terry elo in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    IN
    Inworld TTS-1-MaxInworld
    Bradley-Terry Elo
    1,557.00 elo

    Strengths

    • Ranks #1 of 17 compared models
    • 100th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures TTS Arena V2, not total model capability
  2. 02
    IN
    Inworld TTS-1Inworld
    Bradley-Terry Elo
    1,539.00 elo

    Strengths

    • Ranks #2 of 17 compared models
    • 94th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures TTS Arena V2, not total model capability
  3. 03
    SM
    Smallest.ai
    Bradley-Terry Elo
    1,536.00 elo

    Strengths

    • Ranks #3 of 17 compared models
    • 88th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures TTS Arena V2, not total model capability
  4. 04
    MI
    MiniMax
    Bradley-Terry Elo
    1,528.00 elo

    Strengths

    • Ranks #4 of 17 compared models
    • 81th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures TTS Arena V2, not total model capability
  5. 05
    HA
    Hume AI
    Bradley-Terry Elo
    1,523.00 elo

    Strengths

    • Ranks #5 of 17 compared models
    • 75th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures TTS Arena V2, not total model capability

Selection summary

Best AI Models for TTS Arena V2

Inworld TTS-1-Max currently leads TTS Arena V2 with 1,557.00 elo. 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.

Lightning V3.1 Pro (Jul 2026)
Speech 2.8 HD
Octave TTS
Benchmark rank #1Inworld TTS-1-Max1,557.00 elo
Benchmark rank #2Inworld TTS-11,539.00 elo
Benchmark rank #3Lightning V3.1 Pro (Jul 2026)1,536.00 elo