SHROOM-CAP
Models read answers to questions about scientific papers in nine languages. They flag factual errors and fluency errors separately.
SmurfCat tested Qwen3 judges on the shared task. Five teams submitted blind predictions. Organizers ranked factuality and fluency by macro F1 per language.
- Made by
- CHOMPS shared task organizers
- Released
- July 2025
- Kind
- Faithful to sources
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- Many languages
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Many languages
- Strongest model tested
- gpt-oss-20b #143 on the capability index
- Last model added
- August 2025
- Scores refreshed
- November 20th, 2026
gpt-oss-20b leads with 0.61 gpt-oss-20b leads with 0.61
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so the headline is the plain mean of factuality and fluency macro F1 across nine languages. 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. This view shows only models we track, each at its best.
- 1 gpt-oss-20b Post-evaluation, Zero-shot 0.61
- 2
Gemma 2 9B Post-evaluation, SelfCheckGemma 0.43
- 3 XLM-RoBERTa-Large Post-evaluation, Fine-tuned 0.42
Source: The SHROOM-CAP paper
Source: The SHROOM-CAP paper
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | gpt-oss-20b | 0.61 | Post-evaluation, Zero-shot | CUET_GOODFELLAS | Aug 2025 | Official leaderboard |
| 2 | | 0.43 | Post-evaluation, SelfCheckGemma | Organizers | Jun 2024 | Official leaderboard |
| 3 | XLM-RoBERTa-Large | 0.42 | Post-evaluation, Fine-tuned | AGI | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | gpt-oss-20b | 0.61 | Post-evaluation, Zero-shot | CUET_GOODFELLAS | Aug 2025 | Official leaderboard |
| 2 | | 0.43 | Post-evaluation, SelfCheckGemma | Organizers | Jun 2024 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SHROOM-CAP 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
7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 15 months ago, in August 2025, for gpt-oss-20b. 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 1 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (3 entries).
- Note Models scored Only 2 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 15 months ago, in August 2025, for gpt-oss-20b.
- Note Frontier models None of the top 10 has a score. The strongest tested is gpt-oss-20b (#143).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 2 rows for models we track and 1 other entry 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.