Benchmark Almanac

DRAMA-Eval

Not in model cards

Models generate dialogue with several speakers across multiple turns. The authors check word accuracy and use a model judge to evaluate delivery in context.

Made by
Jingbin Hu and colleagues
Released
October 2026
Kind
Speech recognition and translation
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Subject
Arts
Language
Chinese, English
In and out
Text, Audio → Audio
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Audio and speech
Scores refreshed
November 20th, 2026
17
Entries on its own leaderboard, 2 models we track

Ming-3.0-tts-0.5B leads with 2.55% Ming-3.0-tts-0.5B leads with 2.55%

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. This view shows only models we track, each at its best.

  1. 1 Ming-3.0-tts-0.5B 2.55%
  2. 2 SeedAudio 2.58%
  3. 3 FireRedTTS3 2.64%
  4. 4 Qwen3-TTS (VD) 2.73%
  5. 5 SoulX-Podcast 2.74%
  6. 6 Fun-CosyVoice3-0.5B 2.98%
  7. 7 FireRedTTS2 3.01%
  8. 8 VoxCPM2 3.25%
  9. 9 StepAudio 3 Gen 3.78%
  10. 10 MiniMax H3 3.84%
  11. 11 MOSS-TTSD 4.06%
  12. 12 MOSS-TTS-2.0 Preview 4.28%
  13. 13 Ming-3.0-tts-tiny 4.67%
  14. 14 MiMo-Audio-7B 5.17%
  15. 15 VibeVoice 5.62%
  16. 16 Qwen-Audio-3.1-TTS-Next 5.79%
  17. 17 Higgs Audio V2 8.43%

Source: Official DRAMA-Eval leaderboard

Source: Official DRAMA-Eval leaderboard

#EntryScoreSettingDateSource
1 Ming-3.0-tts-0.5B 2.55% Official leaderboard
2 SeedAudio 2.58% Official leaderboard
3 FireRedTTS3 2.64% Official leaderboard
4 Qwen3-TTS (VD) 2.73% Official leaderboard
5 SoulX-Podcast 2.74% Official leaderboard
6 Fun-CosyVoice3-0.5B 2.98% Official leaderboard
7 FireRedTTS2 3.01% Official leaderboard
8 VoxCPM2 3.25% Official leaderboard
9 StepAudio 3 Gen 3.78% Official leaderboard
10 MiniMax H3 3.84% Official leaderboard
11 MOSS-TTSD 4.06% Official leaderboard
12 MOSS-TTS-2.0 Preview 4.28% Official leaderboard
13 Ming-3.0-tts-tiny 4.67% Official leaderboard
14 MiMo-Audio-7B 5.17% Official leaderboard
15 VibeVoice 5.62% Official leaderboard
16 Qwen-Audio-3.1-TTS-Next 5.79% Official leaderboard
17 Higgs Audio V2 8.43% Official leaderboard
#ModelScoreSettingDateSource
1 Ming-3.0-tts-0.5B 2.55% Official leaderboard
2 MiniMax H3 3.84% Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

No dated values yet.

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 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 (17 entries).
  • Pass Models scored 2 models we track, plus 15 other entries on its leaderboard.
  • Note Newest score No scores yet.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on aslp-lab.github.io: 2 rows for models we track and 15 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