Benchmark Almanac

SuperCLUE-ASR

Hy-ASR-3.0-Preview 6.65% tops its leaderboard GPT-Transcribe 12.1% leads the models we track
Not in model cards

Models transcribe Chinese speech under different acoustic conditions.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Speech recognition and translation
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Language
Chinese
In and out
Audio → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Audio and speech
Last model added
August 2026
Scores refreshed
November 20th, 2026
12
Entries on its own leaderboard, 3 models we track

Hy-ASR-3.0-Preview tops the leaderboard with 6.65% GPT-Transcribe leads with 12.1% among models released by August 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 GPT-Transcribe, at 12.1%. This view shows only models we track, each at its best.

The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Hy-ASR-3.0-Preview API 6.65%
  2. 2 StepAudio-3-ASR API 7.07%
  3. 3 fun-asr-realtime-2026-02-28 API 7.62%
  4. 4 豆包 SeedASR API 8.09%
  5. 5 讯飞录音文件转写大模型 API 8.88%
  6. 6 MAI-Transcribe-2 API 8.91%
  7. 7 Scribe-v2 API 9.15%
  8. 8 GPT-Transcribe API 12.1%
  9. 9 Gemini 3.5 Transcribe API 12.4%
  10. 10 MiMo-V2.5-ASR API 12.8%
  11. 11 GLM-ASR-2512 API 13%
  12. 12 Voxtral Mini Transcribe 2 API 15.7%

Source: Official SuperCLUE-ASR leaderboard

Source: Official SuperCLUE-ASR leaderboard

#EntryScoreSettingDateSource
1 Hy-ASR-3.0-Preview closed weights 6.65% API Official leaderboard
2 StepAudio-3-ASR closed weights 7.07% API Official leaderboard
3 fun-asr-realtime-2026-02-28 closed weights 7.62% API Official leaderboard
4 豆包 SeedASR closed weights 8.09% API Official leaderboard
5 讯飞录音文件转写大模型 closed weights 8.88% API Official leaderboard
6 MAI-Transcribe-2 closed weights 8.91% API Official leaderboard
7 Scribe-v2 closed weights 9.15% API Official leaderboard
8 GPT-Transcribe 12.1% API Jul 2026 Official leaderboard
9 Gemini 3.5 Transcribe 12.4% API Aug 2026 Official leaderboard
10 MiMo-V2.5-ASR open weights 12.8% API Official leaderboard
11 GLM-ASR-2512 closed weights 13% API Official leaderboard
12 Voxtral Mini Transcribe 2 15.7% API Feb 2026 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-Transcribe 12.1% API Jul 2026 Official leaderboard
2 Gemini 3.5 Transcribe 12.4% API Aug 2026 Official leaderboard
3 Voxtral Mini Transcribe 2 15.7% API Feb 2026 Official leaderboard

Rankings by part

We read 23 parts from the benchmark’s own leaderboard in 5 groups: 基础中文转写, 真实声学鲁棒性, 对话与长音频, 专业领域与长尾信息 and 中文高难信息. Each ranks models on one part of the test. Gemini 3.5 Transcribe leads 12 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

基础中文转写↓

3 models we track have a score here.

  1. 1 GPT-Transcribe 1.38%
  2. 2 Gemini 3.5 Transcribe 1.56%
  3. 3 Voxtral Mini Transcribe 2 1.70%

2 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.

Mistral AI OpenAI
Own leaderboard Not tested since Aug 2026

Source: Official SuperCLUE-ASR 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 Best so far
0% 20% 40% 60% 80% 100% 2026 GPT-Transcribe Voxtral Mini Transcribe 2 0% 20% 40% 60% 80% 100% 2026 GPT-Transcribe Voxtral Mini Transcribe 2

Source: Official SuperCLUE-ASR 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

8 of 9 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 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 3 models we track, plus 9 other entries on its leaderboard.
  • Pass Newest score The newest is from August 2026, for Gemini 3.5 Transcribe.
  • 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 superclueai.com: 3 rows for models we track and 9 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