HIPE-OCRepair 2026
Models correct errors in machine transcriptions of historical newspapers and printed works in English, French, and German. They see the transcriptions without the page images.
The organizers rank submissions by the weighted character match error rate across eight test sets. They publish the reference texts and scorer.
- Made by
- HIPE-OCRepair organizers
- Released
- November 2025
- Kind
- Reading in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
bnf-mistral_hipe-ocrepair-bench_v0.9_run1 tops the leaderboard with 0.01
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.
- 1 bnf-mistral_hipe-ocrepair-bench_v0.9_run1 0.01
- 2 bnf-mistral_hipe-ocrepair-bench_v0.9_run3 0.01
- 3 bnf-mistral_hipe-ocrepair-bench_v0.9_run2 0.01
- 4 blocr_hipe-ocrepair-bench_v0.9_run1 0.01
- 5 l3i_hipe-ocrepair-bench_v0.9_run1 0.02
- 6 Zakaria-ENSIAS_hipe-ocrepair-bench_v0.9_run1 0.02
- 7 l3i_hipe-ocrepair-bench_v0.9_run2 0.02
- 8 baseline-no-correction_hipe-ocrepair-bench_v0.9_run1 0.02
Source: Official HIPE-OCRepair 2026 leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | bnf-mistral_hipe-ocrepair-bench_v0.9_run1 | 0.01 0 to 0 | Official leaderboard | ||
| 2 | bnf-mistral_hipe-ocrepair-bench_v0.9_run3 | 0.01 0 to 0 | Official leaderboard | ||
| 3 | bnf-mistral_hipe-ocrepair-bench_v0.9_run2 | 0.01 0 to 0 | Official leaderboard | ||
| 4 | blocr_hipe-ocrepair-bench_v0.9_run1 | 0.01 0 to 0 | Official leaderboard | ||
| 5 | l3i_hipe-ocrepair-bench_v0.9_run1 | 0.02 0 to 0 | Official leaderboard | ||
| 6 | Zakaria-ENSIAS_hipe-ocrepair-bench_v0.9_run1 | 0.02 0 to 0 | Official leaderboard | ||
| 7 | l3i_hipe-ocrepair-bench_v0.9_run2 | 0.02 0 to 0 | Official leaderboard | ||
| 8 | baseline-no-correction_hipe-ocrepair-bench_v0.9_run1 | 0.02 0 to 0 | 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 Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
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 official leaderboard (8 entries).
- Pass Models scored 8 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on hipe-eval.github.io: 8 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.