StepFun (@StepFun_ai)
Step-Audio-R1.1을 소개합니다. 오디오 추론의 새 지평을 표방하며 Artificial Analysis Speech Reasoning 리더보드에서 1위를 차지했다고 발표했습니다. BigBench Audio에서 96.4% 정확도로 신기록을 세워 Grok, Gemini, OpenAI, Google 모델들을 제쳤다고 보고했습니다.
https://x.com/StepFun_ai/status/2011984261705056632
#audioreasoning #bigbench #multimodal #leaderboard
StepFun (@StepFun_ai) on X
🎤 Introducing Step-Audio-R1.1: The New Frontier of Audio Reasoning!
👑 We just hit No.1 on the Artificial Analysis Speech Reasoning leaderboard!
Our results:
✅96.4% accuracy on BigBench Audio, setting a new record and surpassing Grok, Gemini, OpenAI, and Google models (Fig.
StepFun (@StepFun_ai)
Step-Audio-R1.1 발표 — 오디오 추론 분야의 새로운 성과로, Artificial Analysis Speech Reasoning 리더보드에서 1위를 차지했습니다. BigBench Audio에서 96.4% 정확도로 기록을 갱신하며 Grok, Gemini 및 OpenAI·Google 계열 모델들을 능가한 SOTA 결과를 보고했습니다.
https://x.com/StepFun_ai/status/2011845838188822684
#stepaudio #audio #audionlp #bigbench #sota
StepFun (@StepFun_ai) on X
🎤 Introducing Step-Audio-R1.1: The New Frontier of Audio Reasoning!
🏆 We just hit No.1 on the Artificial Analysis Speech Reasoning leaderboard!
Our results:
✅96.4% accuracy on BigBench Audio, setting a new record and surpassing Grok, Gemini, OpenAI, and Google models (Fig.
Beyond the Imitation Game, a collaboratively-built benchmark for measuring and extrapolating the capabilities of language models.
https://github.com/google/BIG-bench#BIGBench #LLM
GitHub - google/BIG-bench: Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models - GitHub - google/BIG-bench: Beyond the Imitation Game collaborative benchmark ...
sayzard
OpenSoul ✅
Savina
Matti Schneider