HalluScoring 2026
Models detect factual errors in Arabic answers. Separate tasks test unseen questions, unseen answer generators and the ability to select a correct alternative.
Hashtag AI ran Gemma 4 on Islamic knowledge and mixed-domain questions. The organizers evaluated submitted systems on hidden tests.
- Made by
- HalluScoring organizers
- Released
- May 2026
- Kind
- Hallucination rates
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Philosophy, ethics and religion
- Language
- Arabic
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- A host
MARBERTv2 + CAMeLBERT-Mix + ARBERT tops the leaderboard with 77.2%
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 MARBERTv2 + CAMeLBERT-Mix + ARBERT REGLAT 77.2%
- 2 ARBERT Baseline_ARBERT 76.4%
- 3 CAMeLBERT AyahVerse 76.3%
- 4 MARBERT Baseline_MARBERT 74.7%
- 5 mBERT Baseline_mBERT 70.1%
- 6 ALLaM-7B Anhnamxtanh 66%
- 7 Qwen2.5-3B-Instruct Scalar_NITK 64.9%
Source: Official HalluScoring 2026 leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | MARBERTv2 + CAMeLBERT-Mix + ARBERT | 77.2% | REGLAT | REGLAT | Official leaderboard | |
| 2 | ARBERT | 76.4% | Baseline_ARBERT | Organizers | Official leaderboard | |
| 3 | CAMeLBERT | 76.3% | AyahVerse | AyahVerse | Official leaderboard | |
| 4 | MARBERT | 74.7% | Baseline_MARBERT | Organizers | Official leaderboard | |
| 5 | mBERT | 70.1% | Baseline_mBERT | Organizers | Official leaderboard | |
| 6 | ALLaM-7B | 66% | Anhnamxtanh | Anhnamxtanh | Official leaderboard | |
| 7 | Qwen2.5-3B-Instruct | 64.9% | Scalar_NITK | Scalar_NITK | 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 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 official leaderboard (7 entries).
- Pass Models scored 7 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 7 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.