Benchmark Almanac

Sumi Japanese PII Corpus

(D) Sumi fp32 0.98 tops its leaderboard
Not in model cards

Models locate personal information in Japanese business templates and prose. The release includes 2,000 template test documents and 520 documents outside those templates.

NVIDIA reports exact-span micro F1 on both splits in its Nemotron PII Japan release. Sumi also evaluates Qwen3-4B-Instruct on smaller samples.

Made by
NagaYu
Released
September 2026
Kind
Reading comprehension
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Risk
Privacy
Language
Japanese
In and out
Text → Text
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Content safety
5
Entries on its own leaderboard, 0 models we track

(D) Sumi fp32 tops the leaderboard with 0.98

Best score per entry from the benchmark's own leaderboard, read on November 21st, 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 (D) Sumi fp32 Template-independent generalisation set, 100 positive and 100 negative documents 0.98
  2. 2 (E) Sumi INT8 Template-independent generalisation set, 100 positive and 100 negative documents 0.95
  3. 3 (C) Local LLM 4B (Q4) Template-independent generalisation set, 100 positive and 100 negative documents 0.82
  4. 4 (B) Presidio + GiNZA Template-independent generalisation set, 100 positive and 100 negative documents 0.24
  5. 5 (A) Presidio, default Template-independent generalisation set, 100 positive and 100 negative documents 0.18

Source: Official Sumi Japanese PII Corpus leaderboard

#EntryScoreSettingDateSource
1 (D) Sumi fp32 0.98 Template-independent generalisation set, 100 positive and 100 negative documents Official leaderboard
2 (E) Sumi INT8 0.95 Template-independent generalisation set, 100 positive and 100 negative documents Official leaderboard
3 (C) Local LLM 4B (Q4) 0.82 Template-independent generalisation set, 100 positive and 100 negative documents Official leaderboard
4 (B) Presidio + GiNZA 0.24 Template-independent generalisation set, 100 positive and 100 negative documents Official leaderboard
5 (A) Presidio, default 0.18 Template-independent generalisation set, 100 positive and 100 negative documents 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

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 (5 entries).
  • Pass Models scored 5 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 github.com: 5 entries at the last read, none a model we track.
  • Pass Last read November 21st, 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