# Raisonnement à l'écoute, Big Bench Audio, édition du 9 novembre 2026

Tableau repris tel que Artificial Analysis le publie : part de bonnes réponses, dites à voix haute, à 1 000 questions de raisonnement posées à l'oral en anglais (Big Bench Audio, tiré de Big Bench Hard : sophismes, orientation, dénombrement, vrai ou faux), notées par un modèle juge. Aucun score de QUELLE IA, aucun score combiné. Édition du 9 novembre 2026.

| Rang | Modèle | Éditeur | Valeur (%) |
| ---: | --- | --- | --- |
| 1 | [StepAudio 3 Realtime](https://quelleia.com/voix/modeles/stepaudio-3-realtime/) | StepFun | 99,7 |
| 2 | [Qwen Audio 3.0 Realtime Plus](https://quelleia.com/voix/modeles/alibaba-qwen-audio-3-0-realtime-plus/) | Alibaba | 99,2 |
| 3 | [Phonic 1 (High)](https://quelleia.com/voix/modeles/phonic-1-high/) | Phonic | 98,9 |
| 4 | [Eleven Realtime v1 Max](https://quelleia.com/voix/modeles/elevenlabs-eleven-realtime-v1-max/) | ElevenLabs | 98,8 |
| 5 | [Qwen3.5-Omni-Plus-Realtime](https://quelleia.com/voix/modeles/alibaba-qwen3-5-omni-plus-realtime/) | Alibaba | 98,7 |
| 6 | [Grok Voice 3.0](https://quelleia.com/voix/modeles/spacexai-grok-voice-3-0/) | SpaceXSI | 98,5 |
| 7 | [Gemini 3.8 Live Extended Thinking](https://quelleia.com/voix/modeles/google-gemini-3-8-live-extended-thinking/) | Google | 97,7 |
| 8 | [Step-Audio R1.1 (Realtime)](https://quelleia.com/voix/modeles/step-audio-r1-1-realtime/) | StepFun | 97,6 |
| 9 | [Grok Voice 2.0](https://quelleia.com/voix/modeles/spacexai-grok-voice-2-0/) | SpaceXSI | 97,2 |
| 10 | [Grok Voice 1.0](https://quelleia.com/voix/modeles/spacexai-grok-voice-1-0/) | SpaceXSI | 97,1 |
| 11 | [Gemini 3.1 Flash Live Preview](https://quelleia.com/voix/modeles/google-gemini-3-1-flash-live-preview/) | Google | 96,6 |
| 11 | [GPT-Realtime-2](https://quelleia.com/voix/modeles/openai-gpt-realtime-2/) | OpenAI | 96,6 |
| 13 | [Qwen Audio 3.0 Realtime Flash](https://quelleia.com/voix/modeles/alibaba-qwen-audio-3-0-realtime-flash/) | Alibaba | 96,1 |
| 14 | [GPT-Realtime-2.1](https://quelleia.com/voix/modeles/openai-gpt-realtime-2-1/) | OpenAI | 95,8 |
| 15 | [Grok Voice Fast 1.0](https://quelleia.com/voix/modeles/spacexai-grok-voice-fast-1-0/) | SpaceXSI | 93,3 |
| 16 | [Gemini 3.8 Live](https://quelleia.com/voix/modeles/google-gemini-3-8-live/) | Google | 91,7 |
| 17 | [Gemini 2.5 Flash Native Audio Dialog Thinking](https://quelleia.com/voix/modeles/google-gemini-2-5-flash-native-audio-dialog-thinking/) | Google | 90,7 |
| 18 | [GPT-Live 1](https://quelleia.com/voix/modeles/openai-gpt-live-1/) | OpenAI | 90,1 |
| 19 | [Amazon Nova 2 Sonic](https://quelleia.com/voix/modeles/amazon-nova-2-sonic/) | Amazon | 88,1 |
| 20 | [Deepslate Opal](https://quelleia.com/voix/modeles/deepslate-opal/) | Deepslate | 85,0 |
| 21 | [GPT-Realtime](https://quelleia.com/voix/modeles/openai-gpt-realtime/) | OpenAI | 83,3 |
| 22 | [GPT-Realtime-1.5](https://quelleia.com/voix/modeles/openai-gpt-realtime-1-5/) | OpenAI | 81,4 |
| 23 | [Eleven Realtime v1 Mini](https://quelleia.com/voix/modeles/elevenlabs-eleven-realtime-v1-mini/) | ElevenLabs | 75,9 |
| 24 | [GPT-Realtime-2.1 Mini](https://quelleia.com/voix/modeles/openai-gpt-realtime-2-1-mini/) | OpenAI | 74,7 |
| 25 | [GPT-4o Mini Realtime](https://quelleia.com/voix/modeles/openai-gpt-4o-mini-realtime/) | OpenAI | 68,9 |
| 26 | [Gemini 2.5 Flash Native Audio Dialog](https://quelleia.com/voix/modeles/google-gemini-2-5-flash-native-audio-dialog/) | Google | 68,6 |
| 26 | [Higgs Realtime](https://quelleia.com/voix/modeles/boson-ai-higgs-realtime/) | Boson AI | 68,6 |
| 28 | [GPT-Realtime Mini](https://quelleia.com/voix/modeles/openai-gpt-realtime-mini/) | OpenAI | 63,6 |
| 29 | [Qwen3.5-Omni-Flash-Realtime](https://quelleia.com/voix/modeles/alibaba-qwen3-5-omni-flash-realtime/) | Alibaba | 59,0 |
| 30 | [Qwen3 Omni 30B A3B Instruct (flash)](https://quelleia.com/voix/modeles/alibaba-qwen3-omni-30b-a3b-instruct-flash/) | Alibaba | 58,7 |
| 31 | [Raon-SpeechChat-9B](https://quelleia.com/voix/modeles/krafton-raon-speechchat-9b/) | KRAFTON | 57,5 |
| 32 | [Qwen3 Omni 30B A3B Instruct (realtime)](https://quelleia.com/voix/modeles/alibaba-qwen3-omni-30b-a3b-instruct-realtime/) | Alibaba | 56,8 |
| 33 | [GPT-4o Audio](https://quelleia.com/voix/modeles/openai-gpt-4o-audio/) | OpenAI | 54,3 |
| 34 | [Freeze-Omni](https://quelleia.com/voix/modeles/vita-freeze-omni/) | VITA | 33,4 |
| 35 | [Nemotron Voicechat](https://quelleia.com/voix/modeles/nvidia-nemotron-voicechat/) | NVIDIA | 27,0 |
| 36 | [PersonaPlex](https://quelleia.com/voix/modeles/nvidia-personaplex-7b-v1/) | NVIDIA | 19,1 |
| 37 | [FLM-Audio](https://quelleia.com/voix/modeles/cofe-ai-flm-audio/) | Cofe AI | 16,0 |
| 38 | [Moshi](https://quelleia.com/voix/modeles/kyutai-moshi/) | Kyutai | 4,4 |

- Source : Artificial Analysis : https://artificialanalysis.ai/speech-to-speech (relevé du 9 novembre 2026)

Source : QUELLE IA, édition du 9 novembre 2026, quelleia.com, d'après Artificial Analysis.