---
title: "The Mighty ToRR — paper by Ashury-Tahan et al. (2026)"
description: "The authors build ToRR, a benchmark that combines 10 existing datasets spanning 6 table tasks (QA, fact verification… 26 references."
authors: ["Shir Ashury-Tahan", "Yifan Mai", "Rajmohan C", "Ariel Gera", "Yotam Perlitz", "Asaf Yehudai", "Elron Bandel", "Leshem Choshen", "Eyal Shnarch", "Percy Liang", "Michal Shmueli-Scheuer"]
year: 2026
venue: "Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)"
source: "https://aclanthology.org/2026.surgellm-1.2/"
doi: "10.18653/v1/2026.surgellm-1.2"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tahan-2026-mighty-torr-benchmark-table-reasoning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tahan-2026-mighty-torr-benchmark-table-reasoning/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/) / The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs

# The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs

**Authors:** Shir Ashury-Tahan, [Yifan Mai](https://md.research.elamur.ai/free/en/authors/yifan-mai/), Rajmohan C, [Ariel Gera](https://md.research.elamur.ai/free/en/authors/ariel-gera/), [Yotam Perlitz](https://md.research.elamur.ai/free/en/authors/yotam-perlitz/), [Asaf Yehudai](https://md.research.elamur.ai/free/en/authors/asaf-yehudai/), [Elron Bandel](https://md.research.elamur.ai/free/en/authors/elron-bandel/), [Leshem Choshen](https://md.research.elamur.ai/free/en/authors/leshem-choshen/), Eyal Shnarch, [Percy Liang](https://md.research.elamur.ai/free/en/authors/percy-liang/) and [Michal Shmueli-Scheuer](https://md.research.elamur.ai/free/en/authors/michal-shmueli-scheuer/) · **Year:** 2026 · **Venue:** [Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)](https://md.research.elamur.ai/free/en/venues/surgellm/) ([Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era 2026](https://md.research.elamur.ai/free/en/venues/surgellm/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.surgellm-1.2/) · [PDF](https://aclanthology.org/2026.surgellm-1.2.pdf) · [DOI 10.18653/v1/2026.surgellm-1.2](https://doi.org/10.18653/v1/2026.surgellm-1.2) · [OpenAlex](https://openalex.org/W7166847767)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
Large language models are often given tables, yet it is unclear how well they reason over them and how much their answers depend on how a table is written out. Earlier evaluations covered few tasks, domains or models and mostly ignored formatting effects. The authors build ToRR, a benchmark that combines 10 existing datasets spanning 6 table tasks (QA, fact verification, table-to-text, data analysis, classification) in domains such as finance, science and Wikipedia. Each input table is rendered in 7 serializations (e.g., JSON, HTML, Markdown, CSV) and optionally altered by 4 structure-preserving perturbations, such as row shuffling or transposition. Fourteen leading LLMs from 7 families were scored on both accuracy and consistency across these variants. Even top systems proved fragile: answers shifted when only the format changed, and no format was best across the board. A meta-evaluation shows that scoring over many prompt configurations makes model rankings more reliable, with a gain comparable to enlarging the test set. ToRR thus offers a more trustworthy way to judge table reasoning.

## Key points
- Datasets: FinQA, TableBench (DA, NR, FC), WikiTQ, TabFact, QTSumm, SciGen, NumericNLG and TURL CTA. All metrics are scaled to [0, 1] so scores can be aggregated.
- Required skills were annotated manually on three levels: knowledge extraction (needed everywhere), textual reasoning and numerical reasoning.
- Prompt variation combines 7 table serializations with 4 perturbations that only reorder content. The benchmark is built with the Unitxt library for reproducibility.
- 14 LLMs (including GPT-4o and DeepSeek v3) were evaluated. Behaviour was brittle and inconsistent, and no single table format consistently performed best.
- The leaderboard, full model outputs and code are publicly released. Stated limitations: only tables embedded directly in the prompt, no hierarchical tables, and reliance on externally defined metrics.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works

## Cite

Cite as: Shir Ashury-Tahan, Yifan Mai, Rajmohan C, Ariel Gera, Yotam Perlitz, Asaf Yehudai, Elron Bandel, Leshem Choshen, Eyal Shnarch, Percy Liang and Michal Shmueli-Scheuer. 2026. The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs. Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{ashurytahan2026mighty,
  title = {{The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs}},
  author = {Shir Ashury-Tahan, Yifan Mai, Rajmohan C, Ariel Gera, Yotam Perlitz, Asaf Yehudai, Elron Bandel, Leshem Choshen, Eyal Shnarch, Percy Liang and Michal Shmueli-Scheuer},
  booktitle = {Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.surgellm-1.2},
  url = {https://doi.org/10.18653/v1/2026.surgellm-1.2}
}
```

- [← previous The L2 Network: A CEFR-Aligned Knowledge Graph for Grammar Domain Modeling](https://md.research.elamur.ai/free/en/papers/flucht-2026-l2-network-cefr-aligned-knowledge/)
- [next → The Model's Language Matters: A Comparative Privacy Analysis of LLMs](https://md.research.elamur.ai/free/en/papers/mishra-2026-model-s-language-matters-comparative/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/)

## References

26 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jorge Osés Grijalba, L Alfonso Urena Lopez, Eugenio Martínez-Cámara, and Jose Camacho-Collados. 2024. Question answering over tabular data with databench: A large-scale empirical evaluation of LLMs. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Reso… [find](https://scholar.google.com/scholar?q=Jorge+Os%C3%A9s+Grijalba%2C+L+Alfonso+Urena+Lopez%2C+Eugenio+Mart%C3%ADnez%2DC%C3%A1mara%2C+and+Jose+Camacho%2DCollados%2E+2024%2E+Question+answering+over+tabular+data+with+databench%3A+A+large%2Dscale+empirical+evaluation+of+LLMs%2E+I)
2. Samuel Ackerman, Eitan Farchi, Orna Raz, and Assaf Toledo. 2025. Statistical multi-metric evaluation and visualization of llm system predictive performance. Preprint, arXiv:2501.18243. — [arXiv:2501.18243](https://arxiv.org/abs/2501.18243) [find](https://scholar.google.com/scholar?q=Samuel+Ackerman%2C+Eitan+Farchi%2C+Orna+Raz%2C+and+Assaf+Toledo%2E+2025%2E+Statistical+multi%2Dmetric+evaluation+and+visualization+of+llm+system+predictive+performance%2E+Preprint%2C+arXiv%3A2501%2E18243%2E+%E2%80%94+%5BarXiv%3A2501%2E1)
3. Norah Alzahrani, Hisham Abdullah Alyahya, Yazeed Alnumay, Sultan Alrashed, Shaykhah Alsubaie, Yusef Almushaykeh, Faisal Mirza, Nouf Alotaibi, Nora Altwairesh, Areeb Alowisheq, M Saiful Bari, and Haidar Khan. 2024. [When benchmarks are targets: Revealing the sensitivity of large language model leaderb…](https://md.research.elamur.ai/free/en/papers/alzahrani-2024-benchmarks-targets-revealing-sensitivity-large/)
4. Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, and Xiaoyong Du. 2022. PASTA: Table-operations aware fact verification via sentence-table cloze pre-training. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4971–4983, Abu Dhabi, United Arab Em… [find](https://scholar.google.com/scholar?q=Zihui+Gu%2C+Ju+Fan%2C+Nan+Tang%2C+Preslav+Nakov%2C+Xiaoman+Zhao%2C+and+Xiaoyong+Du%2E+2022%2E+PASTA%3A+Table%2Doperations+aware+fact+verification+via+sentence%2Dtable+cloze+pre%2Dtraining%2E+In+Proceedings+of+the+2022+Confer)
5. Elron Bandel, Yotam Perlitz, Elad Venezian, Roni Friedman, Ofir Arviv, Matan Orbach, Shachar Don-Yehiya, Dafna Sheinwald, Ariel Gera, Leshem Choshen, Maurice G Kendall and B Babington Smith. 1939. The problem of m rankings. The annals of mathematical statistics, 10(3):275–287. [find](https://scholar.google.com/scholar?q=Elron+Bandel%2C+Yotam+Perlitz%2C+Elad+Venezian%2C+Roni+Friedman%2C+Ofir+Arviv%2C+Matan+Orbach%2C+Shachar+Don%2DYehiya%2C+Dafna+Sheinwald%2C+Ariel+Gera%2C+Leshem+Choshen%2C+Maurice+G+Kendall+and+B+Babington+Smith%2E+1939%2E+The)
6. Yucheng Ruan, Xiang Lan, Jingying Ma, Yizhi Dong, Kai He, and Mengling Feng. 2024. Language modeling on tabular data: A survey of foundations, techniques and evolution. arXiv preprint arXiv:2408.10548. — [arXiv:2408.10548](https://arxiv.org/abs/2408.10548) [find](https://scholar.google.com/scholar?q=Yucheng+Ruan%2C+Xiang+Lan%2C+Jingying+Ma%2C+Yizhi+Dong%2C+Kai+He%2C+and+Mengling+Feng%2E+2024%2E+Language+modeling+on+tabular+data%3A+A+survey+of+foundations%2C+techniques+and+evolution%2E+arXiv+preprint+arXiv%3A2408%2E10548)
7. Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu, Banghua Zhu, Joseph E. Gonzalez, and Ion Stoica. 2024. [From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline](https://md.research.elamur.ai/free/en/papers/li-2024-crowdsourced-data-high-quality-benchmarks/). Preprint, arXiv:2406.11939.
8. Ananya Singha, José Cambronero, Sumit Gulwani, Vu Le, and Chris Parnin. 2023. Tabular representation, noisy operators, and impacts on table structure understanding tasks in LLMs. In NeurIPS 2023 Second Table Representation Learning Workshop. [find](https://scholar.google.com/scholar?q=Ananya+Singha%2C+Jos%C3%A9+Cambronero%2C+Sumit+Gulwani%2C+Vu+Le%2C+and+Chris+Parnin%2E+2023%2E+Tabular+representation%2C+noisy+operators%2C+and+impacts+on+table+structure+understanding+tasks+in+LLMs%2E+In+NeurIPS+2023+Secon)
9. Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher Ré, Diana Acosta-Navas, Drew A. Hudson, and 3… [find](https://scholar.google.com/scholar?q=Percy+Liang%2C+Rishi+Bommasani%2C+Tony+Lee%2C+Dimitris+Tsipras%2C+Dilara+Soylu%2C+Michihiro+Yasunaga%2C+Yian+Zhang%2C+Deepak+Narayanan%2C+Yuhuai+Wu%2C+Ananya+Kumar%2C+Benjamin+Newman%2C+Binhang+Yuan%2C+Bobby+Yan%2C+Ce+Zhang%2C+C)
10. Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura, and Hiroya Takamura. 2021. Towards table-to-text generation with numerical reasoning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference o… [find](https://scholar.google.com/scholar?q=Lya+Hulliyyatus+Suadaa%2C+Hidetaka+Kamigaito%2C+Kotaro+Funakoshi%2C+Manabu+Okumura%2C+and+Hiroya+Takamura%2E+2021%2E+Towards+table%2Dto%2Dtext+generation+with+numerical+reasoning%2E+In+Proceedings+of+the+59th+Annual+Me)
11. Tianyang Liu, Fei Wang, and Muhao Chen. 2023. Rethinking tabular data understanding with large language models. arXiv preprint arXiv:2312.16702. [find](https://scholar.google.com/scholar?q=Tianyang+Liu%2C+Fei+Wang%2C+and+Muhao+Chen%2E+2023%2E+Rethinking+tabular+data+understanding+with+large+language+models%2E+arXiv+preprint+arXiv%3A2312%2E16702%2E)
12. Weizheng Lu, Jing Zhang, Ju Fan, Zihao Fu, Yueguo Chen, and Xiaoyong Du. 2025. Large language model for table processing: a survey. Frontiers of Computer Science, 19(2). [find](https://scholar.google.com/scholar?q=Weizheng+Lu%2C+Jing+Zhang%2C+Ju+Fan%2C+Zihao+Fu%2C+Yueguo+Chen%2C+and+Xiaoyong+Du%2E+2025%2E+Large+language+model+for+table+processing%3A+a+survey%2E+Frontiers+of+Computer+Science%2C+19%282%29%2E)
13. Yuan Sui, Mengyu Zhou, Mingjie Zhou, Shi Han, and Dongmei Zhang. 2024. [Table meets llm: Can large language models understand structured table data? a benchmark and empirical study](https://md.research.elamur.ai/free/en/papers/sui-2023-table-meets-llm-large-language/). Preprint, arXiv:2305.13062.
14. Moran Mizrahi, Guy Kaplan, Daniel Malkin, Rotem Dror, Dafna Shahaf, and Gabriel Stanovsky. 2023. State of what art? a call for multi-prompt llm evaluation. Transactions of the Association for Computational Linguistics, 12:933–949. [find](https://scholar.google.com/scholar?q=Moran+Mizrahi%2C+Guy+Kaplan%2C+Daniel+Malkin%2C+Rotem+Dror%2C+Dafna+Shahaf%2C+and+Gabriel+Stanovsky%2E+2023%2E+State+of+what+art%3F+a+call+for+multi%2Dprompt+llm+evaluation%2E+Transactions+of+the+Association+for+Computat)
15. III Turner, Herbert M and Robert M Bernard. 2006. Calculating and synthesizing effect sizes. Contemporary issues in communication science and disorders, 33(Spring):42–55. [find](https://scholar.google.com/scholar?q=III+Turner%2C+Herbert+M+and+Robert+M+Bernard%2E+2006%2E+Calculating+and+synthesizing+effect+sizes%2E+Contemporary+issues+in+communication+science+and+disorders%2C+33%28Spring%29%3A42%E2%80%9355%2E)
16. Daniel J Wilson. 2019. The harmonic mean p-value for combining dependent tests. Proceedings of the National Academy of Sciences, 116(4):1195–1200. [find](https://scholar.google.com/scholar?q=Daniel+J+Wilson%2E+2019%2E+The+harmonic+mean+p%2Dvalue+for+combining+dependent+tests%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+116%284%29%3A1195%E2%80%931200%2E)
17. Nafise Sadat Moosavi, Andreas Rücklé, Dan Roth, and Iryna Gurevych. 2021. Scigen: a dataset for reasoning-aware text generation from scientific tables. In NeurIPS Datasets and Benchmarks. [find](https://scholar.google.com/scholar?q=Nafise+Sadat+Moosavi%2C+Andreas+R%C3%BCckl%C3%A9%2C+Dan+Roth%2C+and+Iryna+Gurevych%2E+2021%2E+Scigen%3A+a+dataset+for+reasoning%2Daware+text+generation+from+scientific+tables%2E+In+NeurIPS+Datasets+and+Benchmarks%2E)
18. Xianjie Wu, Jian Yang, Linzheng Chai, Ge Zhang, Jiaheng Liu, Xinrun Du, Di Liang, Daixin Shu, Xianfu Cheng, Tianzhen Sun, Guanglin Niu, Tongliang Li, and Zhoujun Li. 2024. Tablebench: A comprehensive and complex benchmark for table question answering. Preprint, arXiv:2408.09174. — [arXiv:2408.09174](https://arxiv.org/abs/2408.09174) [find](https://scholar.google.com/scholar?q=Xianjie+Wu%2C+Jian+Yang%2C+Linzheng+Chai%2C+Ge+Zhang%2C+Jiaheng+Liu%2C+Xinrun+Du%2C+Di+Liang%2C+Daixin+Shu%2C+Xianfu+Cheng%2C+Tianzhen+Sun%2C+Guanglin+Niu%2C+Tongliang+Li%2C+and+Zhoujun+Li%2E+2024%2E+Tablebench%3A+A+comprehensive+)
19. Chaoxu Pang, Yixuan Cao, Chunhao Yang, and Ping Luo. 2024. Uncovering limitations of large language models in information seeking from tables. arXiv preprint arXiv:2406.04113. [find](https://scholar.google.com/scholar?q=Chaoxu+Pang%2C+Yixuan+Cao%2C+Chunhao+Yang%2C+and+Ping+Luo%2E+2024%2E+Uncovering+limitations+of+large+language+models+in+information+seeking+from+tables%2E+arXiv+preprint+arXiv%3A2406%2E04113%2E)
20. Panupong Pasupat and Percy Liang. 2015. [Compositional semantic parsing on semi-structured tables](https://md.research.elamur.ai/free/en/papers/pasupat-2015-compositional-semantic-parsing-semi-structured/). In Annual Meeting of the Association for Computational Linguistics.
21. Yilun Zhao, Zhenting Qi, Linyong Nan, Boyu Mi, Yixin Liu, Weijin Zou, Simeng Han, Ruizhe Chen, Xiangru Tang, Yumo Xu, Dragomir Radev, and Arman Cohan. 2023a. Qtsumm: Query-focused summarization over tabular data. Preprint, arXiv:2305.14303. [find](https://scholar.google.com/scholar?q=Yilun+Zhao%2C+Zhenting+Qi%2C+Linyong+Nan%2C+Boyu+Mi%2C+Yixin+Liu%2C+Weijin+Zou%2C+Simeng+Han%2C+Ruizhe+Chen%2C+Xiangru+Tang%2C+Yumo+Xu%2C+Dragomir+Radev%2C+and+Arman+Cohan%2E+2023a%2E+Qtsumm%3A+Query%2Dfocused+summarization+over+t)
22. Yotam Perlitz, Elron Bandel, Ariel Gera, Ofir Arviv, Liat Ein-Dor, Eyal Shnarch, Noam Slonim, Michal Shmueli-Scheuer, and Leshem Choshen. 2024. Efficient benchmarking of language models. Preprint, arXiv:2308.11696. [find](https://scholar.google.com/scholar?q=Yotam+Perlitz%2C+Elron+Bandel%2C+Ariel+Gera%2C+Ofir+Arviv%2C+Liat+Ein%2DDor%2C+Eyal+Shnarch%2C+Noam+Slonim%2C+Michal+Shmueli%2DScheuer%2C+and+Leshem+Choshen%2E+2024%2E+Efficient+benchmarking+of+language+models%2E+Preprint%2C+arX)
23. Yilun Zhao, Haowei Zhang, Shengyun Si, Linyong Nan, Xiangru Tang, and Arman Cohan. 2023b. Investigating table-to-text generation capabilities of LLMs in real-world information seeking scenarios. arXiv preprint arXiv:2305.14987. — [arXiv:2305.14987](https://arxiv.org/abs/2305.14987) [find](https://scholar.google.com/scholar?q=Yilun+Zhao%2C+Haowei+Zhang%2C+Shengyun+Si%2C+Linyong+Nan%2C+Xiangru+Tang%2C+and+Arman+Cohan%2E+2023b%2E+Investigating+table%2Dto%2Dtext+generation+capabilities+of+LLMs+in+real%2Dworld+information+seeking+scenarios%2E+arXiv)
24. Zipeng Qiu, You Peng, Guangxin He, Binhang Yuan, and Chen Wang. 2024. TQA-Bench: Evaluating LLMs for multi-table question answering with scalable context and symbolic extension. arXiv preprint arXiv:2411.19504. — [arXiv:2411.19504](https://arxiv.org/abs/2411.19504) [find](https://scholar.google.com/scholar?q=Zipeng+Qiu%2C+You+Peng%2C+Guangxin+He%2C+Binhang+Yuan%2C+and+Chen+Wang%2E+2024%2E+TQA%2DBench%3A+Evaluating+LLMs+for+multi%2Dtable+question+answering+with+scalable+context+and+symbolic+extension%2E+arXiv+preprint+arXiv%3A2)
25. Yilun Zhao, Chen Zhao, Linyong Nan, Zhenting Qi, Wenlin Zhang, Xiangru Tang, Boyu Mi, and Dragomir Radev. 2023c. Robut: A systematic study of table QA robustness against human-annotated adversarial perturbations. arXiv preprint arXiv:2306.14321. [find](https://scholar.google.com/scholar?q=Yilun+Zhao%2C+Chen+Zhao%2C+Linyong+Nan%2C+Zhenting+Qi%2C+Wenlin+Zhang%2C+Xiangru+Tang%2C+Boyu+Mi%2C+and+Dragomir+Radev%2E+2023c%2E+Robut%3A+A+systematic+study+of+table+QA+robustness+against+human%2Dannotated+adversarial+pe)
26. Anka Reuel, Amelia Hardy, Chandler Smith, Max Lamparth, Malcolm Hardy, and Mykel J. Kochenderfer. 2024. Betterbench: Assessing ai benchmarks, uncovering issues, and establishing best practices. Preprint, arXiv:2411.12990. [find](https://scholar.google.com/scholar?q=Anka+Reuel%2C+Amelia+Hardy%2C+Chandler+Smith%2C+Max+Lamparth%2C+Malcolm+Hardy%2C+and+Mykel+J%2E+Kochenderfer%2E+2024%2E+Betterbench%3A+Assessing+ai+benchmarks%2C+uncovering+issues%2C+and+establishing+best+practices%2E+Prepri)

*Updated 2 November 2026*