SAC-Bench
Models identify sounds and their order when a spoken claim contradicts the recording. Matched clips test whether answers follow the acoustic evidence.
- Released
- October 2026
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Audio and speech
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
Qwen3-Omni-30B-A3B leads with 91.3% Qwen3-Omni-30B-A3B leads with 91.3%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score. The headline is recording-level balanced accuracy on Event Presence. 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. This view shows only models we track, each at its best.
- 1
Qwen3-Omni-30B-A3B Neutral prompt, Audio-only 91.3%
- 2 Step-Audio-2-mini Neutral prompt, Audio-only 85.8%
- 3 Audio Flamingo Next Neutral prompt, Compatible 85.2%
- 4 MOSS-Audio-8B Neutral prompt, Audio-only 81.2%
- 5 Spatial-Omni (SO-30B) Neutral prompt, Audio-only 73.1%
Source: The SAC-Bench paper
Source: The SAC-Bench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 91.3% | Neutral prompt, Audio-only | Sep 2025 | Official leaderboard |
| 2 | Step-Audio-2-mini | 85.8% | Neutral prompt, Audio-only | Official leaderboard | |
| 3 | Audio Flamingo Next | 85.2% | Neutral prompt, Compatible | Official leaderboard | |
| 4 | MOSS-Audio-8B | 81.2% | Neutral prompt, Audio-only | Official leaderboard | |
| 5 | Spatial-Omni (SO-30B) | 73.1% | Neutral prompt, Audio-only | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 91.3% | Neutral prompt, Audio-only | Sep 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The SAC-Bench paper
Qwen3-Omni-30B-A3B on the official leaderboard passed 85% in September 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SAC-Bench 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
7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (5 entries).
- Pass Models scored 1 model we track, plus 4 other entries on its leaderboard.
- Note Newest score The newest came 14 months ago, in September 2025, for Qwen3-Omni-30B-A3B. That’s expected for a saturated test.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Saturated. The best is 91.3%, past 85% since September 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 3 rows for models we track and 4 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.