Vals AI VoiceCodeBench: leaderboard
Metric: Task Success Rate (%). Source: www.vals.ai. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gpt-live-transcribe | 67.67 |
| 2 | ink-2 | 62 |
| 3 | gpt-4o-transcribe | 59.67 |
| 4 | nova-3-streaming | 59.33 |
| 5 | inworld-stt-1 | 57.33 |
| 6 | whisper-large-v3-turbo | 57 |
| 7 | muse_voice_transcribe | 57 |
| 8 | flux-general-en | 55.67 |
| 9 | chirp_3 | 55.33 |
| 10 | scribe_v2_realtime | 55.33 |
Interactive version: theaggregate.ai/benchmark?slug=vals-ai-voicecodebench · How It Works · Data refreshed daily, snapshot 2026-09-05.