RMS-AQA
Models identify sound events in domestic spaces, then answer questions about their positions and timing. The benchmark scores both stages.
- Made by
- Peihao Chen and colleagues
- Released
- October 2026
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Multi-turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Audio and speech
- Strongest model tested
-
Gemini 3.1 Pro #40 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Qwen3-Omni + SpatialAug tops the leaderboard with 48.9% Qwen3.8-Omni-Flash leads with 36.4% among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen3.8-Omni-Flash, at 36.4%. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- Claude Opus 5.5
- and 16 more
- 1 Qwen3-Omni + SpatialAug 48.9%
- 2 Audio Flamingo Next + SpatialAug 45.2%
- 3 MiDashengLM + SpatialAug 44.7%
- 4 Audio Flamingo 3 + SpatialAug 39.1%
- 5
Qwen3.8-Omni-Flash 36.4%
- 6
Gemini 3.1 Pro 29.6%
- 7 GPT Audio 1.5 17.1%
- 8 Qwen3-Omni 16.7%
- 9 Audio Flamingo Next 15.9%
- 10
Audio Flamingo 3 15.8%
- 11 MiDashengLM 9.40%
Source: Official RMS-AQA leaderboard
- 1
Qwen3.8-Omni-Flash 36.4%
- 2
Gemini 3.1 Pro 29.6%
- 3
Audio Flamingo 3 15.8%
Source: Official RMS-AQA leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen3-Omni + SpatialAug | 48.9% | Official leaderboard | ||
| 2 | Audio Flamingo Next + SpatialAug | 45.2% | Official leaderboard | ||
| 3 | MiDashengLM + SpatialAug | 44.7% | Official leaderboard | ||
| 4 | Audio Flamingo 3 + SpatialAug | 39.1% | Official leaderboard | ||
| 5 | | 36.4% | Sep 2026 | Official leaderboard | |
| 6 | | 29.6% | Feb 2026 | Official leaderboard | |
| 7 | GPT Audio 1.5 | 17.1% | Official leaderboard | ||
| 8 | Qwen3-Omni | 16.7% | Official leaderboard | ||
| 9 | Audio Flamingo Next | 15.9% | Official leaderboard | ||
| 10 | | 15.8% | Jul 2025 | Official leaderboard | |
| 11 | MiDashengLM | 9.40% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 36.4% | Sep 2026 | Official leaderboard | |
| 2 | | 29.6% | Feb 2026 | Official leaderboard | |
| 3 | | 15.8% | Jul 2025 | Official leaderboard |
Rankings by part
We read 12 parts from the benchmark’s own leaderboard in 2 groups: raw stage 2 and grounded stage 2. Each ranks models on one part of the test. Qwen3.8-Omni-Flash leads 11 of them, and Audio Flamingo 3 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
SC
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 57.8%
- 2
Gemini 3.1 Pro 50%
- 3
Audio Flamingo 3 29.5%
SL
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 36.6%
- 2
Audio Flamingo 3 ↑1 31.1%
- 3
Gemini 3.1 Pro ↓1 29.4%
TD
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 68.5%
- 2
Gemini 3.1 Pro 56.4%
- 3
Audio Flamingo 3 28.1%
SR
3 models we track have a score here.
- 1
Audio Flamingo 3 ↑2 39%
- 2
Qwen3.8-Omni-Flash ↓1 38.4%
- 3
Gemini 3.1 Pro ↓1 33.4%
TR
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 64.3%
- 2
Gemini 3.1 Pro 57.2%
- 3
Audio Flamingo 3 40.1%
AP
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 61.6%
- 2
Gemini 3.1 Pro 52.1%
- 3
Audio Flamingo 3 36.2%
SC
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 39.4%
- 2
Gemini 3.1 Pro 32.7%
- 3
Audio Flamingo 3 9.80%
SL
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 24.4%
- 2
Gemini 3.1 Pro 18.3%
- 3
Audio Flamingo 3 14.6%
TD
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 44.1%
- 2
Gemini 3.1 Pro 32.5%
- 3
Audio Flamingo 3 14.6%
SR
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 26.8%
- 2
Gemini 3.1 Pro 22.9%
- 3
Audio Flamingo 3 17.3%
TR
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 43.6%
- 2
Gemini 3.1 Pro 36.8%
- 3
Audio Flamingo 3 20.8%
AP
3 models we track have a score here.
- 1
Qwen3.8-Omni-Flash 40%
- 2
Gemini 3.1 Pro 34.1%
- 3
Audio Flamingo 3 17.6%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official RMS-AQA leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official RMS-AQA leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (11 entries).
- Pass Models scored 3 models we track, plus 8 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for Qwen3.8-Omni-Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.1 Pro (#40).
- Pass Headroom The best is 36.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on rmsaqachallenge.github.io: 3 rows for models we track and 8 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.