# MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

arXiv: https://arxiv.org/abs/2603.28590 · HTML: https://mlsanity.com/paper/2603.28590/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 51 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors](https://mlsanity.com/paper/2507.05246/) (2025)
- [PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory](https://mlsanity.com/paper/2512.06688/) (2025)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents](https://mlsanity.com/paper/2506.15740/) (2025)
- [International AI Safety Report 2026](https://mlsanity.com/paper/2602.21012/) (2026)
- [A Pragmatic Way to Measure Chain-of-Thought Monitorability](https://mlsanity.com/paper/2510.23966/) (2025)
- [AI Deception: Risks, Dynamics, and Controls](https://mlsanity.com/paper/2511.22619/) (2025)
- [Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution](https://mlsanity.com/paper/2602.16154/) (2026)

## Built on by (most cited first, 8 of 8)

- [Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2605.24286/) (2026)
- [How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models](https://mlsanity.com/paper/2608.02089/) (2026)
- [Length Penalties Make Chain-of-Thought Less Monitorable](https://mlsanity.com/paper/2607.09786/) (2026)
- [CoT-Guard: Small Models for Strong Monitoring](https://mlsanity.com/paper/2605.12746/) (2026)
- [The Answer Is Not the Argument](https://mlsanity.com/paper/2609.00264/) (2026)
- [Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection](https://mlsanity.com/paper/2609.15989/) (2026)
- [Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement](https://mlsanity.com/paper/2609.24243/) (2026)
- [On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination](https://mlsanity.com/paper/2610.18727/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (i.e., decision-critical factors) driving the model's behavior, leading to the reduced CoT monitorability problem. This limits the use of CoTs for reliable oversight. However, a comprehensive and fully open-source benchmark for thoroughly evaluating CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize when CoTs can be used to monitor the factors driving LLM behavior; and (2) two prompting stress-test settings to quantify the extent to which CoT monitorability can be degraded. Extensive experiments show that CoT monitorability is a conditional property affected by the evaluated LLM, monitor LLM, and task characteristics. Across these factors, monitorability is higher when decision-critical factors shape the intermediate reasoning process, rather than merely influencing the final answer. Under stress-test prompting, most evaluated LLMs can intentionally reduce monitorability, mainly on tasks where decision-critical factors are not structurally required by the reasoning process. Overall, MonitorBench provides a basis for further research on AI control, reasoning faithfulness, stress-test monitorability, and monitoring scaffords. The code is available at https://github.com/ASTRAL-Group/MonitorBench.