Omnilingua-AudioMC
Models follow requirements across spoken conversations in ten languages. The authors compare each model's spoken and text responses against the same 1,404 rubric items.
- Made by
- Nankai University and Alibaba
- Released
- November 2026
- Kind
- Speech recognition and translation
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- Many languages
- Interaction
- Multi-turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Audio and speech, Many languages
- Strongest model tested
-
Gemini 3.8 Flash #24 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Muse Spark 1.2 leads with 64% among models released by September 2026 Muse Spark 1.2 leads with 64% among models released by September 2026
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. 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.
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
- GPT-6 Astra
- and 16 more
- 1
Muse Spark 1.2 Reference Transcript 64%
- 2
Gemini 3.1 Pro Reference Transcript 63%
- 3 Qwen3.8 Omni Reference Transcript 60.9%
- 4
Gemini 3.8 Flash Reference Transcript 57%
- 5 Doubao Seed Lite Reference Transcript 48.4%
- 6 Qwen3.5 Omni Reference Transcript 40.1%
- 7
Voxtral Small Reference Transcript 30.4%
- 8 Qwen3-Omni Reference Transcript 29%
- 9 Voxtral-Mini Reference Transcript 20.1%
- 10 Qwen2.5-Omni Reference Transcript 13.8%
Source: The Omnilingua-AudioMC paper
Source: The Omnilingua-AudioMC paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 64% | Reference Transcript | Aug 2026 | Official leaderboard |
| 2 | | 63% | Reference Transcript | Feb 2026 | Official leaderboard |
| 3 | Qwen3.8 Omni | 60.9% | Reference Transcript | Official leaderboard | |
| 4 | | 57% | Reference Transcript | Sep 2026 | Official leaderboard |
| 5 | Doubao Seed Lite | 48.4% | Reference Transcript | Official leaderboard | |
| 6 | Qwen3.5 Omni | 40.1% | Reference Transcript | Official leaderboard | |
| 7 | | 30.4% | Reference Transcript | Jul 2025 | Official leaderboard |
| 8 | Qwen3-Omni | 29% | Reference Transcript | Official leaderboard | |
| 9 | Voxtral-Mini | 20.1% | Reference Transcript | Official leaderboard | |
| 10 | Qwen2.5-Omni | 13.8% | Reference Transcript | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 64% | Reference Transcript | Aug 2026 | Official leaderboard |
| 2 | | 63% | Reference Transcript | Feb 2026 | Official leaderboard |
| 3 | | 57% | Reference Transcript | Sep 2026 | Official leaderboard |
| 4 | | 30.4% | Reference Transcript | Jul 2025 | Official leaderboard |
Rankings by part
We read 10 parts from the benchmark’s paper, each ranking models on one part of the test, such as English, Chinese and Japanese. Gemini 3.1 Pro leads 5 of them, and Muse Spark 1.2 leads the other 5. Arrows show how far a model moved from its overall rank among the models we track.
English
4 models we track have a score here.
- 1
Gemini 3.1 Pro ↑1 66.9%
- 2
Muse Spark 1.2 ↓1 64.7%
- 3
Gemini 3.8 Flash 59.3%
- 4
Voxtral Small 29%
Chinese
4 models we track have a score here.
- 1
Gemini 3.1 Pro ↑1 65.5%
- 2
Muse Spark 1.2 ↓1 62.4%
- 3
Gemini 3.8 Flash 58.8%
- 4
Voxtral Small 29.9%
Japanese
4 models we track have a score here.
- 1
Gemini 3.1 Pro ↑1 65%
- 2
Muse Spark 1.2 ↓1 64%
- 3
Gemini 3.8 Flash 57.9%
- 4
Voxtral Small 29.7%
Spanish
4 models we track have a score here.
- 1
Gemini 3.1 Pro ↑1 64.1%
- 2
Muse Spark 1.2 ↓1 63.8%
- 3
Gemini 3.8 Flash 55.4%
- 4
Voxtral Small 33.6%
French
4 models we track have a score here.
- 1
Muse Spark 1.2 66.7%
- 2
Gemini 3.1 Pro 63.3%
- 3
Gemini 3.8 Flash 54.5%
- 4
Voxtral Small 34.5%
Russian
4 models we track have a score here.
- 1
Muse Spark 1.2 67.5%
- 2
Gemini 3.1 Pro 62.1%
- 3
Gemini 3.8 Flash 57.9%
- 4
Voxtral Small 31.6%
German
4 models we track have a score here.
- 1
Muse Spark 1.2 65%
- 2
Gemini 3.1 Pro 63.3%
- 3
Gemini 3.8 Flash 58.8%
- 4
Voxtral Small 27.8%
Italian
4 models we track have a score here.
- 1
Muse Spark 1.2 63.6%
- 2
Gemini 3.1 Pro 63.3%
- 3
Gemini 3.8 Flash 56.8%
- 4
Voxtral Small 35.6%
Thai
4 models we track have a score here.
- 1
Gemini 3.1 Pro ↑1 61.9%
- 2
Muse Spark 1.2 ↓1 61.3%
- 3
Gemini 3.8 Flash 55.9%
- 4
Voxtral Small 24.9%
Vietnamese
4 models we track have a score here.
- 1
Muse Spark 1.2 60.9%
- 2
Gemini 3.1 Pro 59.6%
- 3
Gemini 3.8 Flash 56.5%
- 4
Voxtral Small 29.7%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The Omnilingua-AudioMC paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Reference Transcript | 64% | ||||
| Reference Transcript | 63% | ||||
| Full Transcript | 60.8% | ||||
| History Transcript | 60.1% | ||||
| Full Transcript | 58.6% | ||||
| Current Transcript | 57.1% | ||||
| Reference Transcript | 57% | ||||
| Direct Audio | 54.4% | ||||
| Full Transcript | 54.4% | ||||
| History Transcript | 53.2% | ||||
| History Transcript | 52.5% | ||||
| Current Transcript | 50.8% | ||||
| Direct Audio | 50% | ||||
| Current Transcript | 38.6% | ||||
| Direct Audio | 32.4% | ||||
| Reference Transcript | 30.4% | ||||
| Direct Audio | 28.1% |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The Omnilingua-AudioMC paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Reference Transcript | 64% | ||||
| Reference Transcript | 63% | ||||
| Full Transcript | 60.8% | ||||
| History Transcript | 60.1% | ||||
| Full Transcript | 58.6% | ||||
| Current Transcript | 57.1% | ||||
| Reference Transcript | 57% | ||||
| Direct Audio | 54.4% | ||||
| Full Transcript | 54.4% | ||||
| History Transcript | 53.2% | ||||
| History Transcript | 52.5% | ||||
| Current Transcript | 50.8% | ||||
| Direct Audio | 50% | ||||
| Current Transcript | 38.6% | ||||
| Direct Audio | 32.4% | ||||
| Reference Transcript | 30.4% | ||||
| Direct Audio | 28.1% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Omnilingua-AudioMC paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Omnilingua-AudioMC 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 benchmark’s paper (10 entries).
- Pass Models scored 4 models we track, plus 6 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for Gemini 3.8 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.8 Flash (#24).
- Pass Headroom The best is 64%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 17 rows for models we track and 6 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.