Subscribe
Benchmarks
verified 2026-11. Download on Hugging Face
93 of 93
SaveFull-duplexTierSettingFocus
—Speech-nativeLabSpeech-LM Instruction following242025-06
Full-Duplex-Bench v1NTU / UC Berkeley / UW / MIT
Full-duplexSpeech-nativeLab—142025-03
—LegacyLabASR132024-01
Big Bench AudioArtificial Analysis
—Speech-nativeLabSpeech-LM Instruction following122026-05
DuplexActDong et al.
Full-duplexSpeech-nativeLab—82026-10
Full-Duplex-Bench v1.5NTU / UC Berkeley / UW / MIT
Full-duplexSpeech-nativeLab—62025-08
Full-Duplex-Bench v3NTU (NVIDIA advisory)
Full-duplexSpeech-nativeLiveVertical agent62026-05
URO-BenchRuiqi Yan et al.
—Speech-nativeLabSpeech-LM Instruction following +152025-08
MMARSJTU / MBZUAI · NeurIPS 2025
—ComponentLabAudio understanding Speech-LM52026-02
Full-duplexSpeech-nativeVerticalVertical agent Speech-LM52026-10
—ComponentLabSpeech translation ASR52020-07
VideoFDBNVIDIA / David AI
Full-duplexSpeech-nativeLive—42026-10
AIR-BenchAlibaba DAMO (OFA-Sys)
—Speech-nativeLabAudio understanding Instruction following42024-12
Audio MultiChallengeScale AI (Scale Labs)
Full-duplexSpeech-nativeLabSpeech-LM42026-10
TurnBenchSesame AI Labs / Mundo AI / CMU / oto
Full-duplexSpeech-nativeLab—32026-11
Talking TurnsApple / CMU
Full-duplexSpeech-nativeLabSpeech-LM32025-04
Seed-TTS EvalByteDance
—ComponentLabTTS32024-11
Full-Duplex-Bench v2NTU / UC Berkeley / UW / MIT
Full-duplexSpeech-nativeLiveSpeech-LM22026-02
MultiPartyTurnBenchMathur and Manocha
Full-duplexSpeech-nativeLab—22026-10
M3-DuplexBenchNTT (Fukuda et al.)
Full-duplexSpeech-nativeLabSpeech-LM22026-10
VocalBenchSJTU (OmniAgent)
—Speech-nativeLabSpeech-LM Audio understanding12026-01
—Speech-nativeArenaSpeech-LM TTS12026-03
EVA-BenchServiceNow
—Speech-nativeVerticalVertical agent Speech-LM12026-10
HumDial (ICASSP '26)ICASSP 2026 Spoken Dialogue Challenge
Full-duplexSpeech-nativeLabSpeech-LM Emotion12026-01
SD-EvalAcademic (SD-Eval authors)
—ComponentLabSpeech-LM Emotion12024-06
J-Moshi (subjective)Ohashi et al.
Full-duplexSpeech-nativeLabSpeech-LM12025-06
MultiTalkBenchWang et al. (MultiTalk)
Full-duplexSpeech-nativeLab—02026-09
Duplex-MPEMa et al.
Full-duplexSpeech-nativeLab—02026-11
DuplexLedgerLi et al.
Full-duplexSpeech-nativeLabSpeech-LM02026-10
InteractionBenchAvera Labs (He et al.)
Full-duplexSpeech-nativeLiveSpeech-LM02026-11
ECHOZhao et al.
Full-duplexSpeech-nativeLab—02026-09
MP-BenchShih et al.
Full-duplexSpeech-nativeLabSpeech-LM02026-10
DuplexSpeechBench-IFEvalMathur and Manocha
Full-duplexSpeech-nativeLabInstruction following02026-09
—Speech-nativeLabSpeech-LM Vertical agent02026-08
IFEval-AudioAudioLLMs (I2R Singapore)
—Speech-nativeLabInstruction following Speech-LM02025-05
—AdjacentArenaTTS02026-10
—Speech-nativeArenaSpeech-LM Vertical agent02026-10
—ComponentArenaTTS Speech-LM +202026-07
MTalk-BenchFreedomIntelligence / CUHK-SZ
—Speech-nativeArenaSpeech-LM Instruction following +102025-09
TTS ArenaHugging Face
—AdjacentArenaTTS02026-03
VAmoS BenchVeris AI
—Speech-nativeVerticalVertical agent02026-10
APEX-VoiceMathur and Manocha
Full-duplexSpeech-nativeVerticalVertical agent02026-09
VoiceAgentEvalMeituan / Xbench / Agora
—Speech-nativeVerticalVertical agent Speech-LM02025-10
—AdjacentVerticalVertical agent Instruction following02025-05
—ComponentLabSpeech translation02023-12
NV-BenchNi et al.
—ComponentLabTTS Emotion02026-03
SUPERBNTU et al. (s3prl)
—LegacyLabSpeech-LM ASR +102024-06
—LegacyLabEmotion Audio understanding02023-06
SID-BenchXia et al.
Full-duplexSpeech-nativeLab—02026-03
FD-BenchPeng et al.
Full-duplexSpeech-nativeLab—02025-07
MTR-DuplexBenchZhang et al.
Full-duplexSpeech-nativeLabSpeech-LM02026-04
FLEXIGe et al.
Full-duplexSpeech-nativeLab—02025-09
AudioBenchAudioLLMs (I2R Singapore)
—ComponentLabAudio understanding02024-07
Dynamic-SUPERBNTU et al.
—ComponentLabSpeech-LM Instruction following02024-11
—ComponentLabSpeech-LM Instruction following02025-09
ProsAuditAcademic (ProsAudit authors)
—ComponentLabEmotion Audio understanding02023-02
VocalBench-zhSJTU (OmniAgent)
—Speech-nativeLabSpeech-LM Audio understanding02025-11
CS3-BenchAcademic (CS3-Bench authors)
—Speech-nativeLabSpeech-LM02025-10
VoiceAgentBenchAcademic (VoiceAgentBench authors)
—Speech-nativeVerticalVertical agent Speech-LM +102026-02
MSI-BenchBoson AI
—Speech-nativeLabSpeech-LM Vertical agent02026-09
MMedFDAcademic (MMedFD authors)
Full-duplexAdjacentVerticalASR Vertical agent02025-09
—Speech-nativeLabAudio safety Speech-LM02026-05
SpeechJBBCeccatelli, Jeon, Adelani et al.
—Speech-nativeLabAudio safety Speech-LM02026-08
AIA — Acoustic Interference AttackWang, Huang, Liang, Wu (CUHK · HKUST)
—Speech-nativeLabAudio safety Speech-LM02026-05
Omni-DuplexEvalOpenBMB (Tsinghua University / Shanghai Qi Zhi Institute / ModelBest)
Full-duplexAdjacentLabAudio understanding02026-07
OmniInteractCUHK MMLab / SJTU / NTU / McMaster / CityUHK / JUFE
Full-duplexSpeech-nativeLiveAudio understanding02026-05
ProVoice-BenchShanghai Jiao Tong University (Xu et al.)
—Speech-nativeLabSpeech-LM Audio understanding02026-06
eot-benchLiveKit
Full-duplexSpeech-nativeLab—02026-11
Audio2ToolRivian and Volkswagen Group Technologies
—Speech-nativeLabSpeech-LM Vertical agent02026-09
C3 BenchmarkMa et al.
—Speech-nativeLabSpeech-LM02025-10
—Speech-nativeVerticalVertical agent Speech-LM02026-11
Full-duplexSpeech-nativeLive—02026-11
CoDeTTBairong (BRVoice team)
Full-duplexSpeech-nativeLab—02026-04
ContextDialogSeoul National University (Kim et al.)
—Speech-nativeLabSpeech-LM02025-05
—ComponentLiveASR TTS +102026-11
DuplexWorldCentific / University of Maryland
Full-duplexSpeech-nativeVerticalVertical agent02026-08
Game-Time BenchmarkMIT / NTU / Academia Sinica
Full-duplexSpeech-nativeLabInstruction following02026-06
IHBenchBoson AI
—Speech-nativeLabSpeech-LM Vertical agent02026-06
—Speech-nativeLabSpeech-LM Instruction following02026-08
—Speech-nativeVerticalVertical agent Speech-LM02026-11
OpenAudioBenchBaichuan Inc.
—Speech-nativeLabSpeech-LM02025-01
RoleBreakUniversity of Hong Kong / Kami AI
—Speech-nativeLabSpeech-LM Emotion02026-09
S2S-ArenaFreedomIntelligence / CUHK-SZ / Shenzhen University of Advanced Technology
—Speech-nativeLabSpeech-LM Instruction following +102026-06
SpeechInstructBenchCUHK / Alibaba Group
—Speech-nativeLabInstruction following Speech-LM02026-01
SteerBenchScale AI / University of Maryland
—Speech-nativeLabSpeech-LM Instruction following02026-11
TELEVALChina Telecom AI (Tele-AI)
—Speech-nativeLabSpeech-LM Audio understanding +102026-08
TPI-BenchSeoul National University / Yonsei University / University of Seoul
—Speech-nativeLabSpeech-LM Audio understanding02026-04
VERADuke University / Adobe
—Speech-nativeLabSpeech-LM02025-09
VoiceBench-jaSB Intuitions
—Speech-nativeLabSpeech-LM Instruction following02026-03
VoxEvalCUHK / Lightspeed Studios / NUS
—Speech-nativeLabSpeech-LM02025-07
WavBenchXiamen University / Zhejiang University / CUHK-Shenzhen
—Speech-nativeLabSpeech-LM Emotion +102026-02
—Speech-nativeLabSpeech-LM Audio understanding02026-04
WildSpeech-BenchTencent (WeChat AI)
—Speech-nativeLabSpeech-LM02025-09