Benchmark Almanac

CLEF 2025 SimpleText Task 2

BERT Classifier 0.95 tops its leaderboard
Not in model cards
Version 2025

Models flag unsupported sentences, classify distortions in simplified scientific text, or rewrite Cochrane abstracts while avoiding new claims.

Organizers manually labeled 2,659 sentences for distortion type. The SINAI team used Llama 3.1 for detection, and DS@GT used Llama to revise generated text.

Released
November 2024
Kind
Faithful to sources
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Run by
A host
9
Entries in its paper, 0 models we track

BERT Classifier tops the leaderboard with 0.95

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The headline is F1 for posthoc detection, which the organizers identify as the main task. 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 BERT Classifier 0.95
  2. 2 Extra Trees 0.95
  3. 3 Random Forest 0.94
  4. 4 Support Vector Classifier 0.88
  5. 5 XGBoost 0.87
  6. 6 llama-3.3-70b-versatile 0.86
  7. 7 Logistic Regression 0.86
  8. 8 facebook/bart-large-mnli 0.57
  9. 9 gpt4o (snapshot unspecified) 0.35

Source: The CLEF 2025 SimpleText Task 2 paper

#EntryScoreSettingSubmitted byDateSource
1 BERT Classifier 0.95 DSGT Official leaderboard
2 Extra Trees 0.95 DUTH Official leaderboard
3 Random Forest 0.94 DUTH Official leaderboard
4 Support Vector Classifier 0.88 DUTH Official leaderboard
5 XGBoost 0.87 DUTH Official leaderboard
6 llama-3.3-70b-versatile 0.86 DSGT Official leaderboard
7 Logistic Regression 0.86 DUTH Official leaderboard
8 facebook/bart-large-mnli 0.57 DSGT Official leaderboard
9 gpt4o (snapshot unspecified) 0.35 UBOnlp 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 Factuality

All 164 in Factuality
  • SimpleVQA In use Models answer 2,025 short factual questions about images across 9 tasks and 9 topics. An LLM judge grades answers against fixed references. Qwen3.7-Plus 81.7%
  • HallusionBench In use Models answer 1,129 yes or no questions about 346 images, built in pairs to expose language hallucination and visual illusion. Scored by accuracy. Keye-VL-2.0-30B-A3B 73.5%
  • SimpleQA Verified In use 1,000 human-verified, de-duplicated short-answer factual questions measuring parametric knowledge. Gemini 3.1 Pro 77.5%
  • AA-Omniscience v1.1 In use Models answer 3,000 knowledge questions in six domains without tools and may abstain. The index adds correct answers and subtracts wrong ones. Inkling 2 Small 16.1
  • GaRAGe In use Models write long-form RAG answers to 2,366 questions with human-annotated grounding passages. Scoring checks whether answers use the relevant passages. Amazon Nova Pro 60.7%
  • Kimi Hallu Bench In use Models answer hard prompts drawn from practical work tasks. Fact-checking agents score the share of claims that are hallucinated. GPT-6 Astra 4.20%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 9 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 ceur-ws.org: 9 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