LIMMITS 2024
Version 2024
Speech models read text in a target voice across seven languages. Native listeners score naturalness and speaker similarity on the same prompts.
NVIDIA entered P-Flow in the zero-shot track. The organizers ranked seven systems there and specified 144 utterances per listening evaluation.
- Made by
- Indian Institute of Science and LIMMITS organizers
- Released
- September 2023
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Graded by people
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Many languages
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- Anyone
- In views
- Audio and speech, Many languages
TalTech tops the leaderboard with 4
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.
Bars start at 2.5.
- 1 TalTech Track 1: Few-shot, challenge data 4
- 2 NVIDIA Track 3: Zero-shot, external data allowed 4
- 3 SJTU_XLANCE_VC Track 2: Few-shot, external data allowed 4
- 4 THU_HCSI Track 1: Few-shot, challenge data 4
- 5 NLP_POSTECH Track 1: Few-shot, challenge data 4
- 6 LIMITLESS Track 2: Few-shot, external data allowed 4
- 7 MAIS_Speech_2024 Track 2: Few-shot, external data allowed 3
- 8 reply_2024 Track 3: Zero-shot, external data allowed 3
- 9 Shabdh Track 3: Zero-shot, external data allowed 3
- 10 MIDAS Track 1: Few-shot, challenge data 3
- 11 nwpu Track 1: Few-shot, challenge data 3
Source: Official LIMMITS 2024 leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | TalTech | 4 | Track 1: Few-shot, challenge data | TalTech | docs.google.com | Official leaderboard | |
| 2 | NVIDIA | 4 | Track 3: Zero-shot, external data allowed | NVIDIA | docs.google.com | Official leaderboard | |
| 3 | SJTU_XLANCE_VC | 4 | Track 2: Few-shot, external data allowed | SJTU_XLANCE_VC | docs.google.com | Official leaderboard | |
| 4 | THU_HCSI | 4 | Track 1: Few-shot, challenge data | THU_HCSI | docs.google.com | Official leaderboard | |
| 5 | NLP_POSTECH | 4 | Track 1: Few-shot, challenge data | NLP_POSTECH | docs.google.com | Official leaderboard | |
| 6 | LIMITLESS | 4 | Track 2: Few-shot, external data allowed | LIMITLESS | docs.google.com | Official leaderboard | |
| 7 | MAIS_Speech_2024 | 3 | Track 2: Few-shot, external data allowed | MAIS_Speech_2024 | docs.google.com | Official leaderboard | |
| 8 | reply_2024 | 3 | Track 3: Zero-shot, external data allowed | reply_2024 | docs.google.com | Official leaderboard | |
| 9 | Shabdh | 3 | Track 3: Zero-shot, external data allowed | Shabdh | docs.google.com | Official leaderboard | |
| 10 | MIDAS | 3 | Track 1: Few-shot, challenge data | MIDAS | docs.google.com | Official leaderboard | |
| 11 | nwpu | 3 | Track 1: Few-shot, challenge data | nwpu | docs.google.com | Official 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.
Versions
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 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (11 entries).
- Pass Models scored 11 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on sites.google.com: 11 entries at the last read, none a model we track.
- 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.