Benchmark Almanac

CLEF HIPE 2026

Spinfo 0.75 tops its leaderboard
Not in model cards
Version 2026

Models decide whether a historical text places a person at a named location. Organizers rank systems by balanced accuracy across three labels.

The organizers evaluated 17 teams on historical newspapers. They tested transfer to early modern French literature in a separate ranking.

Released
September 2025
Kind
Reasoning in many languages
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
German, English, French
In and out
Text → Text
Interaction
Single turn
Run by
Anyone
18
Entries on its own leaderboard, 0 models we track

Spinfo tops the leaderboard with 0.75

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. 1 Spinfo run1 0.75
  2. 2 MaxFo-Ajie run1 0.70
  3. 3 whereami run1 0.69
  4. 4 Awakened run3 0.67
  5. 5 INSA Lyon run1 0.64
  6. 6 gipplab run2 0.63
  7. 7 Hansel&Gretel run3 0.62
  8. 8 MILRIT run3 0.60
  9. 9 UMUTEAM run2 0.59
  10. 10 Ministral-3-3B-Instruct GGUF baseline 0.2.2 random seed 42 run1 0.58
  11. 11 VerbaNexAI II run3 0.58
  12. 12 BIU_NLP run2 0.58
  13. 13 DS@GT_HIPE run1 0.51
  14. 14 VerbaNexAI I run2 0.48
  15. 15 FI-CODE run2 0.47
  16. 16 ROSTI run3 0.46
  17. 17 FourBytes run1 0.41
  18. 18 Random Decision Baseline run1 0.40

Source: Official CLEF HIPE 2026 leaderboard

#EntryScoreSettingSubmitted byDateSource
1 Spinfo 0.75 run1 Universität zu Köln Official leaderboard
2 MaxFo-Ajie 0.70 run1 Foshan University Official leaderboard
3 whereami 0.69 run1 Alexandria University Official leaderboard
4 Awakened 0.67 run3 National University of Science and Technology Politehnica Bucharest Official leaderboard
5 INSA Lyon 0.64 run1 INSA Lyon - University of Lyon Official leaderboard
6 gipplab 0.63 run2 University of Göttingen Official leaderboard
7 Hansel&Gretel 0.62 run3 IIT Roorkee Official leaderboard
8 MILRIT 0.60 run3 University of Toulouse & La Rochelle University Official leaderboard
9 UMUTEAM 0.59 run2 Universidad de Murcia Official leaderboard
10 Ministral-3-3B-Instruct GGUF baseline 0.2.2 random seed 42 0.58 run1 HIPE-2026 organizers Official leaderboard
11 VerbaNexAI II 0.58 run3 Universidad Tecnológica de Bolívar Official leaderboard
12 BIU_NLP 0.58 run2 Bar-Ilan University Official leaderboard
13 DS@GT_HIPE 0.51 run1 Georgia Institute of Technology Official leaderboard
14 VerbaNexAI I 0.48 run2 Universidad Tecnológica de Bolívar Official leaderboard
15 FI-CODE 0.47 run2 University of the Bundeswehr Munich Official leaderboard
16 ROSTI 0.46 run3 Université Lumière Lyon Official leaderboard
17 FourBytes 0.41 run1 Sri Sivasubramaniya Nadar College of Engineering Official leaderboard
18 Random Decision Baseline 0.40 run1 HIPE-2026 organizers 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.

Versions

More in Multilingual

All 545 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 (18 entries).
  • Pass Models scored 18 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: 18 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