SpotSoundBench
Qwen3.8-Omni-Flash 67.2% 
Audio Flamingo 3 7.60% leads since April 2026 Qwen3.8-Omni-Flash 67.2% leads since September 2026 Models find the time span of short sound events hidden in long, unstructured YouTube recordings. It has 400 audio, query and timestamp triplets.
Released with the SpotSound method paper. Qwen reports it as audio grounding.
- Released
- April 2026
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Last in a launch post
- September 2026
- Last model added
- September 2026
- Scores refreshed
- November 12th, 2026
Qwen3.8-Omni-Flash leads with 67.2%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
Audio Flamingo 3 leads with 7.60% across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.
Qwen3.8-Omni-Flash leads with 67.2%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.
Source: Labs’ model cards
- 1 Audio Flamingo 3 7.60%
- 2 Qwen2-Audio-7B-Instruct 4.40%
- 3 Kimi-Audio-7B-Instruct 3.20%
Source: Official SpotSoundBench leaderboard
- 1 Qwen3.8-Omni-Flash 67.2%
- 2 Audio Flamingo 3 7.60%
- 3 Qwen2-Audio-7B-Instruct 4.40%
- 4 Kimi-Audio-7B-Instruct 3.20%
Sources: Labs’ model cards and official SpotSoundBench leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen3.8-Omni-Flash | 67.2% | Sep 2026 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Audio Flamingo 3 | 7.60% | Jul 2025 | Official leaderboard | |
| 2 | Qwen2-Audio-7B-Instruct | 4.40% | Aug 2024 | Official leaderboard | |
| 3 | Kimi-Audio-7B-Instruct | 3.20% | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen3.8-Omni-Flash | 67.2% | Sep 2026 | Lab model card | |
| 2 | Audio Flamingo 3 | 7.60% | Jul 2025 | Official leaderboard | |
| 3 | Qwen2-Audio-7B-Instruct | 4.40% | Aug 2024 | Official leaderboard | |
| 4 | Kimi-Audio-7B-Instruct | 3.20% | Apr 2025 | Official leaderboard |
The benchmark's own leaderboard has 10 entries, 3 of them models we track. Switch the scores above to rank them together.
Number one over time Number one over time 2 models have held number one with claims included since its release in April 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SpotSoundBench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official SpotSoundBench leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Sep 18, 2026 | Qwen3.8-Omni-Flash | 67.2 | SpotSoundBench Audio Grounding |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Sep 22, 2026 | Qwen3.8-Omni-Flash technical report | 67.2 | SpotSoundBench (Table 4) | Capabilities |
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7% - MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00% - VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%