Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Audio · Audio Captioning · AudioCapsTasks/Audio/Audio Captioning
Audio Captioning · benchmark dataset · 2019 · EN

AudioCaps.

Audio generation quality evaluated on AudioCaps captions

Submit a result
§ 01 · Leaderboard

Best published scores.

7 results indexed across 5 metrics. Shaded row marks current SOTA; ties broken by submission date.


Primary
spider · higher is better
All metrics
cider, r-1, r-10, r-5, spider
cider
1 row
#ModelOrgSubmittedPaper / codecider
01Audio Flamingo 3Jul 2025Audio Flamingo 3: Advancing Audio Intelligence with Full… · code0.700
r-1
1 row
#ModelOrgSubmittedPaper / coder-1
01CLAP (HTSAT-RoBERTa, fusion, K2C Aug.; T->A)Nov 2022Large-scale Contrastive Language-Audio Pretraining with … · code35.10
r-10
1 row
#ModelOrgSubmittedPaper / coder-10
01CLAP (HTSAT-RoBERTa, fusion, K2C Aug.; T->A)Nov 2022Large-scale Contrastive Language-Audio Pretraining with … · code83.70
r-5
1 row
#ModelOrgSubmittedPaper / coder-5
01CLAP (HTSAT-RoBERTa, fusion, K2C Aug.; T->A)Nov 2022Large-scale Contrastive Language-Audio Pretraining with … · code71.90
spider· primary
3 rows
#ModelOrgSubmittedPaper / codespider
01AudioCaps baseline (TopDown+Align)OSSKim et al.Apr 2026editorial0.369
02EnCLAP-baseOSSKAIST / NAVERApr 2026editorial0.300
03PengiOSSMicrosoftApr 2026editorial0.271
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

1 steps
of state of the art.

Each row below marks a model that broke the previous record on spider. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · spider
  1. Apr 5, 2026AudioCaps baseline (TopDown+Align)Kim et al.0.369
Fig 3 · SOTA-setting models only. 1 entries span Apr 2026 Apr 2026.
§ 04 · Literature

2 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies