TabFact
Models decide whether a statement is entailed or refuted by a Wikipedia table. Classification accuracy measures agreement with human labels.
The released split has 12,779 test statements. Tasks combine language interpretation with operations over table values.
- Made by
- UC Santa Barbara and Tencent AI Lab
- Released
- September 2019
- Kind
- Faithful to sources
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
In the authors’ words
The problem of verifying whether a textual hypothesis holds based on the given evidence, also known as fact verification, plays an important role in the study of natural language understanding and semantic representation. However, existing studies are mainly restricted to dealing with unstructured evidence (e.g., natural language sentences and documents, news, etc), while verification under structured evidence, such as tables, graphs, and databases, remains under-explored. This paper specifically aims to study the fact verification given semi-structured data as evidence. To this end, we construct a large-scale dataset called TabFact with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED. TabFact is challenging since it involves both soft linguistic reasoning and hard symbolic reasoning. To address these reasoning challenges, we design two different models: Table-BERT and Latent Program Algorithm (LPA). Table-BERT leverages the state-of-the-art pre-trained language model to encode the linearized tables and statements into continuous vectors for verification. LPA parses statements into programs and executes them against the tables to obtain the returned binary value for verification. Both methods achieve similar accuracy but still lag far behind human performance. We also perform a comprehensive analysis to demonstrate great future opportunities. The data and code of the dataset are provided in https://github.com/wenhuchen/Table-Fact-Checking.
LPA-Ranking w/ Discriminator (Caption) tops the leaderboard with 65.3%
Best score per entry from the benchmark's paper, read on November 18th, 2026. A paper’s table doesn’t add newer models. 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 LPA-Ranking w/ Discriminator (Caption) 65.3%
- 2 Table-BERT Horizontal-F+T-Template 65.1%
- 3 LPA-Ranking w/ Discriminator 65%
- 4 NSM w/ LPA-guided ML + RL 63.5%
- 5 LPA-Weighted-Voting 63.1%
- 6 LPA-Voting w/o Discriminator 58.2%
- 7 NSM w/ RL (Binary Reward) 54.1%
- 8 BERT classifier w/o Table 50.5%
Source: The TabFact paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | LPA-Ranking w/ Discriminator (Caption) | 65.3% | Official leaderboard | ||
| 2 | Table-BERT | 65.1% | Horizontal-F+T-Template | Official leaderboard | |
| 3 | LPA-Ranking w/ Discriminator | 65% | Official leaderboard | ||
| 4 | NSM w/ LPA-guided ML + RL | 63.5% | Official leaderboard | ||
| 5 | LPA-Weighted-Voting | 63.1% | Official leaderboard | ||
| 6 | LPA-Voting w/o Discriminator | 58.2% | Official leaderboard | ||
| 7 | NSM w/ RL (Binary Reward) | 54.1% | Official leaderboard | ||
| 8 | BERT classifier w/o Table | 50.5% | 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 All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (8 entries).
- Pass Models scored 8 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 arxiv.org: 8 entries at the last read, none a model we track.
- Pass Last read November 18th, 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.