Benchmark Almanac

SuperCLUE-Voice (speech interaction)

讯飞星火(实时语音) 76.2 tops its leaderboard GPT-4o Nov 2024 73.0 leads the models we track
Not in model cards

Models interact with users through speech in real time.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Speech recognition and translation
Level
Everyday
Scored
Graded by people
Answers
Open-ended
Measures
Capability
Language
Chinese
In and out
Audio → Audio
Interaction
Multi-turn
Refresh
One fixed set
Run by
A host
In views
Audio and speech
Strongest model tested
GPT-4o Nov 2024 #161 on the capability index
Last model added
November 2024
Scores refreshed
November 20th, 2026
8
Entries on its own leaderboard, 1 model we track

讯飞星火(实时语音) tops the leaderboard with 76.2 GPT-4o leads with 73.0

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-4o, at 73.0. This view shows only models we track, each at its best.

  1. 1 讯飞星火(实时语音) Xiaomi 12T Pro / 安卓端APP / 4.0.18 76.2
  2. 2 GPT-4o Nov 2024, Xiaomi 12T Pro / 安卓端APP / 1.2024.310 73.0
  3. 3 豆包(实时语音) Xiaomi 12T Pro / 安卓端APP / 6.4.0 70.8
  4. 4 海螺AI(实时语音) Xiaomi 12T Pro / 安卓端APP / 2.28.1 69.6
  5. 5 智谱清言(实时语音) Xiaomi 12T Pro / 安卓端APP / 2.6.5 60.8
  6. 6 通义(实时语音) Xiaomi 12T Pro / 安卓端APP / 3.19.0 59.8
  7. 7 Kimi(实时语音) Xiaomi 12T Pro / 安卓端APP / 1.6.5 59.3
  8. 8 文小言(实时语音) Xiaomi 12T Pro / 安卓端APP / 4.4.5.10 47.5

Source: Official SuperCLUE-Voice (speech interaction) leaderboard

Source: Official SuperCLUE-Voice (speech interaction) leaderboard

#EntryScoreSettingReleasedRun onSource
1 讯飞星火(实时语音) 76.2 Xiaomi 12T Pro / 安卓端APP / 4.0.18 Dec 2024 Official leaderboard
2 GPT-4o Nov 2024 73.0 Xiaomi 12T Pro / 安卓端APP / 1.2024.310 Nov 2024 Dec 2024 Official leaderboard
3 豆包(实时语音) 70.8 Xiaomi 12T Pro / 安卓端APP / 6.4.0 Dec 2024 Official leaderboard
4 海螺AI(实时语音) 69.6 Xiaomi 12T Pro / 安卓端APP / 2.28.1 Dec 2024 Official leaderboard
5 智谱清言(实时语音) 60.8 Xiaomi 12T Pro / 安卓端APP / 2.6.5 Dec 2024 Official leaderboard
6 通义(实时语音) 59.8 Xiaomi 12T Pro / 安卓端APP / 3.19.0 Dec 2024 Official leaderboard
7 Kimi(实时语音) 59.3 Xiaomi 12T Pro / 安卓端APP / 1.6.5 Dec 2024 Official leaderboard
8 文小言(实时语音) 47.5 Xiaomi 12T Pro / 安卓端APP / 4.4.5.10 Dec 2024 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 GPT-4o Nov 2024 73.0 Xiaomi 12T Pro / 安卓端APP / 1.2024.310 Nov 2024 Dec 2024 Official leaderboard

Scores over time

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

On the benchmark’s own leaderboard
73.0 2025 73.0 2025

Source: Official SuperCLUE-Voice (speech interaction) 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

7 of 9 checks pass, 2 warnings. 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 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (8 entries).
  • Pass Models scored 1 model we track, plus 7 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in November 2024, for GPT-4o.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4o (#161).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 1 row for models we track and 7 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