Benchmark Almanac

SeniorTalk

Paraformer-large 14.4% tops its leaderboard Whisper large-v3 23.8% leads the models we track
Not in model cards

Models transcribe conversations with older Mandarin speakers and identify who speaks.

The publisher reports model results.

Made by
BAAI FlagEval
Released
March 2025
Kind
Speech recognition and translation
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Chinese
In and out
Audio → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Audio and speech
Last model added
November 2023
Scores refreshed
November 20th, 2026
9
Entries on its own leaderboard, 1 model we track

Paraformer-large tops the leaderboard with 14.4% Whisper large-v3 leads with 23.8%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The headline is character error rate on speech recognition, the first task. Lower values indicate fewer errors. 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 Whisper large-v3, at 23.8%. This view shows only models we track, each at its best.

  1. 1 Paraformer-large Fine-tuning 14.4%
  2. 2 Whisper large-v3 Fine-tuning 23.8%
  3. 3 Whisper-medium Fine-tuning 25.8%
  4. 4 Whisper-small Fine-tuning 28.7%
  5. 5 E-Branchformer Trained from scratch 33.3%
  6. 6 Conformer Trained from scratch 34.6%
  7. 7 Whisper-base Fine-tuning 38.2%
  8. 8 Transformer Trained from scratch 49%
  9. 9 Whisper-tiny Fine-tuning 58.8%

Source: Official SeniorTalk leaderboard

Source: Official SeniorTalk leaderboard

#EntryScoreSettingDateSource
1 Paraformer-large 0.2B 14.4% Fine-tuning Official leaderboard
2 Whisper large-v3 23.8% Fine-tuning Nov 2023 Official leaderboard
3 Whisper-medium 0.8B 25.8% Fine-tuning Official leaderboard
4 Whisper-small 0.2B 28.7% Fine-tuning Official leaderboard
5 E-Branchformer 0B 33.3% Trained from scratch Official leaderboard
6 Conformer 0B 34.6% Trained from scratch Official leaderboard
7 Whisper-base 0.1B 38.2% Fine-tuning Official leaderboard
8 Transformer 0B 49% Trained from scratch Official leaderboard
9 Whisper-tiny 0B 58.8% Fine-tuning Official leaderboard
#ModelScoreSettingDateSource
1 Whisper large-v3 23.8% Fine-tuning Nov 2023 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 Best so far
0% 20% 40% 60% 80% 100% 2024 Whisper large-v3 Whisper large-v3 0% 20% 40% 60% 80% 100% 2024 Whisper large-v3 Whisper large-v3

Source: Official SeniorTalk 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 Newest score check. The newest came 3 years ago, in November 2023, for Whisper large-v3. Every benchmark

Catalog record 2 pass
  • Pass Task access All 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 (9 entries).
  • Pass Models scored 1 model we track, plus 8 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in November 2023, for Whisper large-v3.
  • 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 github.com: 2 rows for models we track and 8 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