Benchmark Almanac

SuperCLUE Arena Text to Speech

ULingo-TTS-1.0-Preview 1,406 tops its leaderboard Gemini 3.8 Flash TTS 1,010 leads the models we track
Not in model cards

Models synthesize speech from text. The arena ranks systems from pairwise comparisons.

The arena reports median ratings and uncertainty intervals.

Made by
SuperCLUE
Kind
Speech recognition and translation
Level
Everyday
Scored
Ranked by matches
Answers
Open-ended
Tasks
All public
Measures
Preference
Language
Chinese
In and out
Text → Audio
Interaction
Single turn
Items from
Live play or votes
Refresh
Live
Run by
A host
Last model added
September 2026
Scores refreshed
November 20th, 2026
14
Entries on its own leaderboard, 3 models we track

ULingo-TTS-1.0-Preview tops the leaderboard with 1,406 Gemini 3.8 Flash TTS leads with 1,010 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 Gemini 3.8 Flash TTS, at 1,010. 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:

Bars start at 400.

  1. 1 ULingo-TTS-1.0-Preview 1,406
  2. 2 Doubao-Seed-TTS 2.0 1,164
  3. 3 讯飞-超拟人语音合成 1,136
  4. 4 Cartesia Sonic 3.6 1,075
  5. 5 Qwen-Audio-3.1-TTS-Flash 1,073
  6. 6 Eleven v4 1,050
  7. 7 Speech-2.6-HD 1,027
  8. 8 Gemini 3.8 Flash TTS 1,010
  9. 9 StepAudio3TTS 984
  10. 10 Qwen3-TTS-Flash 974
  11. 11 Azure Neural 953
  12. 12 gemini-2.5-flash-preview-tts 838
  13. 13 百度智能云-语音合成 737
  14. 14 GPT-4o Mini TTS 573

Source: Official SuperCLUE Arena Text to Speech leaderboard

Source: Official SuperCLUE Arena Text to Speech leaderboard

#EntryScore ±SettingDateSource
1 ULingo-TTS-1.0-Preview 1,406 1354.5 to 1461.5 Official leaderboard
2 Doubao-Seed-TTS 2.0 1,164 ±24.1 Official leaderboard
3 讯飞-超拟人语音合成 1,136 ±24.6 Official leaderboard
4 Cartesia Sonic 3.6 1,075 997.2 to 1145 Official leaderboard
5 Qwen-Audio-3.1-TTS-Flash 1,073 ±76.9 Official leaderboard
6 Eleven v4 1,050 ±71.5 Official leaderboard
7 Speech-2.6-HD 1,027 1003.8 to 1049.7 Official leaderboard
8 Gemini 3.8 Flash TTS 1,010 934.3 to 1080.1 Sep 2026 Official leaderboard
9 StepAudio3TTS 984 918.5 to 1055.9 Official leaderboard
10 Qwen3-TTS-Flash 974 950.2 to 999.2 Sep 2025 Official leaderboard
11 Azure Neural 953 ±24.1 Official leaderboard
12 gemini-2.5-flash-preview-tts 838 814.7 to 862 Official leaderboard
13 百度智能云-语音合成 737 ±23.7 Official leaderboard
14 GPT-4o Mini TTS 573 546.3 to 598.1 Mar 2025 Official leaderboard
#ModelScore ±SettingDateSource
1 Gemini 3.8 Flash TTS 1,010 934.3 to 1080.1 Sep 2026 Official leaderboard
2 Qwen3-TTS-Flash 974 950.2 to 999.2 Sep 2025 Official leaderboard
3 GPT-4o Mini TTS 573 546.3 to 598.1 Mar 2025 Official leaderboard

3 models have held number one on the official leaderboard since 2023

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

OpenAI Qwen Google DeepMind
Own leaderboard Not tested since Sep 2026

Source: Official SuperCLUE Arena Text to Speech 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
600 800 1,000 2025 2026 600 800 1,000 2025 2026

Source: Official SuperCLUE Arena Text to Speech 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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (14 entries).
  • Pass Models scored 3 models we track, plus 11 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 3.8 Flash TTS.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 3 rows for models we track and 11 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