# How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains

arXiv: https://arxiv.org/abs/2601.08134 · HTML: https://mlsanity.com/paper/2601.08134/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 26 of 26)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning](https://mlsanity.com/paper/2002.04326/) (2020)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)
- [Topology Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1710.10370/) (2017)
- [CommonsenseQA 2.0: Exposing the Limits of AI through Gamification](https://mlsanity.com/paper/2201.05320/) (2022)
- [LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning](https://mlsanity.com/paper/2007.08124/) (2020)
- [Reasoning Models Better Express Their Confidence](https://mlsanity.com/paper/2505.14489/) (2025)
- [LEXam: Benchmarking Legal Reasoning on 340 Law Exams](https://mlsanity.com/paper/2505.12864/) (2025)
- [Finetuning Language Models to Emit Linguistic Expressions of Uncertainty](https://mlsanity.com/paper/2409.12180/) (2024)
- [Calibrating LLM Confidence by Probing Perturbed Representation Stability](https://mlsanity.com/paper/2505.21772/) (2025)

## Built on by (most cited first, 4 of 4)

- [Calibrated Triage, Not Autonomy: Confidence Estimation for Medical Vision-Language Models](https://mlsanity.com/paper/2606.15910/) (2026)
- [TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs](https://mlsanity.com/paper/2608.00422/) (2026)
- [Confidence Estimation for Financial Vision-Language Models in Chart and Document Understanding](https://mlsanity.com/paper/2608.06532/) (2026)
- [Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models](https://mlsanity.com/paper/2610.05472/) (2026)

## Abstract (arXiv)

The miscalibration of Large Reasoning Models (LRMs) undermines their reliability in high-stakes domains, necessitating methods to accurately estimate the confidence of their long-form, multi-step outputs. To address this gap, we introduce the Reasoning Model Confidence estimation Benchmark (RMCB), a public resource of 347,496 reasoning traces from six popular LRMs across different architectural families. The benchmark is constructed from a diverse suite of datasets spanning high-stakes domains, including clinical, financial, legal, and mathematical reasoning, alongside complex general reasoning benchmarks, with correctness annotations provided for all samples. Using RMCB, we conduct a large-scale empirical evaluation of over ten distinct representation-based methods, spanning sequential, graph-based, and text-based architectures. Our central finding is a persistent trade-off between discrimination (AUROC) and calibration (ECE): text-based encoders achieve the best AUROC (0.672), while structurally-aware models yield the best ECE (0.148), with no single method dominating both. Furthermore, we find that increased architectural complexity does not reliably outperform simpler sequential baselines, suggesting a performance ceiling for methods relying solely on chunk-level hidden states. This work provides the most comprehensive benchmark for this task to date, establishing rigorous baselines and demonstrating the limitations of current representation-based paradigms.