Codesota · Computer Vision · Optical Character Recognition · dartTasks/Computer Vision/Optical Character Recognition
Optical Character Recognition · benchmark dataset · 2020 · EN

dart.

Dataset from Papers With Code

Submit a result ↵
§ 01 · Leaderboard

Best published scores.

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

Primary
accuracy · higher is better
All metrics
bert, bleu, bleurt, factspotter, meteor, mover, ter
bert
6 rows
#ModelOrgSubmittedPaper / codebert
01T5B Baseline—Oct 2023papers-with-code · code0.951
02FactT5B—Oct 2023papers-with-code · code0.951
03JointGT Baseline—Oct 2023papers-with-code · code0.949
04FactJointGT—Oct 2023papers-with-code · code0.949
05GPT-2-Large (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.940
06HTLM (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.940
bleu
6 rows
#ModelOrgSubmittedPaper / codebleu
01T5B Baseline—Oct 2023papers-with-code · code48.47
02FactT5B—Oct 2023papers-with-code · code48.37
03JointGT Baseline—Oct 2023papers-with-code · code47.51
04FactJointGT—Oct 2023papers-with-code · code47.39
05HTLM (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …47.20
06GPT-2-Large (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …47
bleurt
6 rows
#ModelOrgSubmittedPaper / codebleurt
01T5B Baseline—Oct 2023papers-with-code · code0.675
02FactT5B—Oct 2023papers-with-code · code0.674
03JointGT Baseline—Oct 2023papers-with-code · code0.673
04FactJointGT—Oct 2023papers-with-code · code0.673
05GPT-2-Large (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.400
06HTLM (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.400
factspotter
4 rows
#ModelOrgSubmittedPaper / codefactspotter
01FactT5B—Oct 2023papers-with-code · code97.60
02FactJointGT—Oct 2023papers-with-code · code97.25
03T5B Baseline—Oct 2023papers-with-code · code96.65
04JointGT Baseline—Oct 2023papers-with-code · code95.86
meteor
6 rows
#ModelOrgSubmittedPaper / codemeteor
01T5B Baseline—Oct 2023papers-with-code · code0.407
02FactT5B—Oct 2023papers-with-code · code0.407
03JointGT Baseline—Oct 2023papers-with-code · code0.404
04FactJointGT—Oct 2023papers-with-code · code0.403
05HTLM (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.390
06GPT-2-Large (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.390
mover
2 rows
#ModelOrgSubmittedPaper / codemover
01HTLM (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.510
02GPT-2-Large (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.510
ter
2 rows
#ModelOrgSubmittedPaper / codeter
01GPT-2-Large (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.460
02HTLM (fine-tuning)—Jul 2021HTLM: Hyper-Text Pre-Training and Prompting of Language …0.440
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.
§ 04 · Literature

1 paper
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