Benchmark Almanac

CLEF 2026 SimpleText Task 2

BERT 0.74 tops its leaderboard Qwen3-4B 0.34 leads the models we track
Not in model cards
Version 2026

Models detect or classify unsupported additions to simplified Cochrane abstracts. A generation subtask compares rewrites made with and without explicit checks against the source.

The detection test holds out 2,851 documents. The Amsterdam team tested Qwen3 and GPT-4.1 mini on the new error categories.

Released
September 2025
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
Items from
Real work and use
Run by
A host
Last model added
April 2025
Scores refreshed
November 20th, 2026
6
Entries on its own leaderboard, 1 model we track

BERT tops the leaderboard with 0.74 Qwen3-4B leads with 0.34

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. The best model we track is Qwen3-4B, at 0.34. This view shows only models we track, each at its best.

  1. 1 BERT Without source text 0.74
  2. 2 DeBERTa Without source text 0.74
  3. 3 RoBERTa Without source text 0.74
  4. 4 SciBERT Without source text 0.73
  5. 5 StdlibLogReg Without source text 0.58
  6. 6 Qwen3-4B Without source text 0.34

Source: Official CLEF 2026 SimpleText Task 2 leaderboard

Source: Official CLEF 2026 SimpleText Task 2 leaderboard

#EntryScoreSettingSubmitted byDateSource
1 BERT 0.74 Without source text, BertOnly_bert THM Official leaderboard
2 DeBERTa 0.74 Without source text, crossencoder AIIRLab Official leaderboard
3 RoBERTa 0.74 Without source text, BertOnly_roberta THM Official leaderboard
4 SciBERT 0.73 Without source text, BertOnly_scibert THM Official leaderboard
5 StdlibLogReg 0.58 Without source text, StdlibLogReg SIM Official leaderboard
6 Qwen3-4B 0.34 Without source text, SourceFree_Qwen3-4B AIIRLab Apr 2025 Official leaderboard
#ModelScoreSettingSubmitted byDateSource
1 Qwen3-4B 0.34 Without source text, SourceFree_Qwen3-4B AIIRLab Apr 2025 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
0.34 2025 0.34 2025

Source: Official CLEF 2026 SimpleText Task 2 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for Qwen3-4B. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 1 model we track, plus 5 other entries on its leaderboard.
  • Warning Newest score The newest came 19 months ago, in April 2025, for Qwen3-4B.
  • Note Frontier models None of its models are on the capabilities index.
  • 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: 1 row for models we track and 5 other entries at the last read.
  • 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