New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
VoiceBench benchmark
AI model leaderboard for the VoiceBench benchmark. Compare how large language models score on VoiceBench, see the full ranking, and understand what this AI benchmark measures. NVIDIA Nemotron 3 Nano Omni currently leads with 89.4%. Benchmark for LLM-based voice assistants on spoken instructions.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | NVIDIA Nemotron 3 Nano Omni | NVIDIA | 89.4% | official ↗ |
Frequently asked questions about VoiceBench
What is the VoiceBench benchmark?
Benchmark for LLM-based voice assistants on spoken instructions.
How is the VoiceBench benchmark scored?
VoiceBench is scored using the accuracy (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on VoiceBench?
As of the latest reported scores on GenAIList, NVIDIA Nemotron 3 Nano Omni achieves the highest result on VoiceBench with a score of 89.4%.
Is a higher VoiceBench score better?
Yes. On VoiceBench a higher score indicates better performance, so models near the top of the leaderboard are the strongest.