Benchmark Almanac

WenetSpeech-Chuan-Eval

Paraformer-WSC-Finetune + internal data 13.4% tops its leaderboard
Not in model cards

Models transcribe Sichuanese speech. Qwen reports separate error rates on the easy and hard test sets.

Made by
Yuhang Dai and colleagues
Released
September 2025
Kind
Speech recognition and translation
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Chinese
In and out
Audio → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Audio and speech
13
Entries in its paper, 0 models we track

Paraformer-WSC-Finetune + internal data tops the leaderboard with 13.4%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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.

  1. 1 Paraformer-WSC-Finetune + internal data 13.4%
  2. 2 Paraformer + internal data 13.8%
  3. 3 Paraformer-WSC-Finetune 14.6%
  4. 4 Qwen2.5-omni-WSC-Finetune + internal data 14.8%
  5. 5 FireRedASR-AED [ 16 ] 15.1%
  6. 6 Qwen2.5-omni+internal data 15.1%
  7. 7 FireRedASR-LLM [ 16 ] 15.4%
  8. 8 Qwen2.5-omni-WSC-Finetune 15.7%
  9. 9 Paraformer [ 20 ] 16.5%
  10. 10 Qwen2.5-omni [ 17 ] 17.7%
  11. 11 Kimi-Audio [ 15 ] 18.7%
  12. 12 SenseVoice-small [ 18 ] 19.3%
  13. 13 Whisper [ 19 ] 55.5%

Source: The WenetSpeech-Chuan-Eval paper

#EntryScoreSettingDateSource
1 Paraformer-WSC-Finetune + internal data 13.4% Official leaderboard
2 Paraformer + internal data 13.8% Official leaderboard
3 Paraformer-WSC-Finetune 14.6% Official leaderboard
4 Qwen2.5-omni-WSC-Finetune + internal data 14.8% Official leaderboard
5 FireRedASR-AED [ 16 ] 15.1% Official leaderboard
6 Qwen2.5-omni+internal data 15.1% Official leaderboard
7 FireRedASR-LLM [ 16 ] 15.4% Official leaderboard
8 Qwen2.5-omni-WSC-Finetune 15.7% Official leaderboard
9 Paraformer [ 20 ] 16.5% Official leaderboard
10 Qwen2.5-omni [ 17 ] 17.7% Official leaderboard
11 Kimi-Audio [ 15 ] 18.7% Official leaderboard
12 SenseVoice-small [ 18 ] 19.3% Official leaderboard
13 Whisper [ 19 ] 55.5% 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.

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 benchmark’s paper (13 entries).
  • Pass Models scored 13 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 13 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.

How we check