Benchmark Almanac

RMS-AQA

Qwen3-Omni + SpatialAug 48.9% tops its leaderboard Qwen3.8-Omni-Flash 36.4% leads the models we track
Not in model cards

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
In and out
Text, Audio → Text
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
11
Entries on its own leaderboard, 3 models we track

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:

  1. 1 Qwen3-Omni + SpatialAug 48.9%
  2. 2 Audio Flamingo Next + SpatialAug 45.2%
  3. 3 MiDashengLM + SpatialAug 44.7%
  4. 4 Audio Flamingo 3 + SpatialAug 39.1%
  5. 5 Qwen3.8-Omni-Flash 36.4%
  6. 6 Gemini 3.1 Pro 29.6%
  7. 7 GPT Audio 1.5 17.1%
  8. 8 Qwen3-Omni 16.7%
  9. 9 Audio Flamingo Next 15.9%
  10. 10 Audio Flamingo 3 15.8%
  11. 11 MiDashengLM 9.40%

Source: Official RMS-AQA leaderboard

#EntryScoreSettingDateSource
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 Qwen3.8-Omni-Flash 36.4% Sep 2026 Official leaderboard
6 Gemini 3.1 Pro 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 Audio Flamingo 3 15.8% Jul 2025 Official leaderboard
11 MiDashengLM 9.40% Official leaderboard
#ModelScoreSettingDateSource
1 Qwen3.8-Omni-Flash 36.4% Sep 2026 Official leaderboard
2 Gemini 3.1 Pro 29.6% Feb 2026 Official leaderboard
3 Audio Flamingo 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. 1 Qwen3.8-Omni-Flash 57.8%
  2. 2 Gemini 3.1 Pro 50%
  3. 3 Audio Flamingo 3 29.5%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen
Own leaderboard Not tested since Oct 2026

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.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Qwen3.8-Omni-Flash Gemini 3.1 Pro Audio Flamingo 3 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Qwen3.8-Omni-Flash Gemini 3.1 Pro

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

All 695 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.

How we check