Ming-Lite-Omni-1.5: benchmark results
Provider: Other. Access: Open.
Unified ELO 1493 ± 20, rank #766 of 1605 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SonicBench - Counting | 65 | Accuracy (%; number of sound events (PicoAudio); 100 recogni | 80.6 |
| SonicBench - Texture | 94 | Accuracy (%; sound texture (ESC-50); 100 recognition and 100 | 79.7 |
| SonicBench - Duration | 53 | Accuracy (%; sound-event duration (TAU); 100 recognition and | 69.4 |
| SonicBench | 57 | Accuracy (%; mean over 12 physical attributes of 100 recogni | 67.7 |
| SonicBench - Loudness | 53 | Accuracy (%; loudness (integrated LUFS contrasts of at least | 62.9 |
| SonicBench - Reverberation | 53 | Accuracy (%; reverberation (SRIR room impulse responses); 10 | 62.9 |
| SonicBench - Timbre | 57 | Accuracy (%; instrument timbre (NSynth); 100 recognition and | 62.9 |
| SonicBench - Pitch | 57 | Accuracy (%; pitch height (NSynth notes, one-semitone contra | 58.1 |
| MOV-Bench - Hypothetical Reasoning | 35 | Accuracy (%; 60 hypothetical-reasoning questions; direct inf | 57.1 |
| MOV-Bench - Intent Reasoning | 50 | Accuracy (%; 80 intent-reasoning questions; direct inference | 57.1 |
| SonicBench - Brightness | 52 | Accuracy (%; spectral brightness (NSynth); 100 recognition a | 50 |
| MOV-Bench | 49.52 | Accuracy (%; 519 audio-visual multi-hop multiple-choice ques | 42.9 |
Interactive version: theaggregate.ai/model?slug=ming-lite-omni-1-5 · How It Works · Data refreshed daily, snapshot 2026-09-26.