Rethinking Confidence In Reasoning Models

Rethinking Confidence in Reasoning Models | Cohere Skip to content Rerank 5 is here: sharper search, fewer tokens. Now with Context Focus. Learn more

Products

Solutions

Resources

Blog

Research

Company

Sign in

Request a demo

Platform North

Enterprise-ready AI for business

Compass

Intelligent search and discovery

Models Command

Generative language models

Transcribe

Speech recognition model

North Small Translate

Machine translation model

Parse New

Document parsing model

Embed New

Semantic representation model

Rerank New

Retrieval optimization model

Models Overview

Product Products Overview

Total Cost of AI Ownership

Pricing

Featured North 2: Cohere's latest platform update — with 15+ new features

Deploy Model Vault

Dedicated model inference platform

Private Deployments

On-prem or isolated VPCs

Security

Protect your data at every stage

See deployment options

By Industry Financial Services

Public Sector

Technology

Telecommunications

Energy and Utilities

Healthcare

Life Sciences

Manufacturing

Featured Model Vault provides fully-isolated, performant inference with Saas simplicity

Insights Customer Stories

For Developers Developers

Models Overview

Docs

Discord

LLM University

Connect Partners

Events

Webinars

Merch Store

Featured How CoreWeave used Cohere North to transform its customer support in 90 days

Blog

The latest news, launches, and insights

Read more

Cohere to acquire AISLE to advance cyber-resilient sovereign AI

North 2: Enterprise AI without compromises

Introducing Embed 5—A new family of frontier embedding models

Research Cohere Labs

Cohere’s ML research lab

Explorations Future(s) of Work

How will AI change the way we work?

Aya Models

Multilingual AI at scale

All Papers

Initiatives Research Scholars

Finding the new generation of ML talent

Open Science Community

Championing global, open science

Catalyst Grants

Supporting impactful ML endeavors

Resources Blog

Hugging Face

Events

Featured The future of work debate has an evidence problem

About

Careers

Newsroom

Oct 20, 2026

6 minute read

Rethinking confidence in reasoning models

You roll two fair six-sided dice. What is the probability that their sum is at least 10?

A model might hesitate at first. Then it counts the possibilities: three ways to roll 10, two ways to roll 11, and one way to roll 12. Six outcomes out of 36. The answer is 1/6 .

In our illustrative example (figure below, on the left), the model starts at 25% confidence and finishes at 88%. Those percentages describe its confidence in getting the answer right, not the probability of the dice outcome. Working through the problem has changed its assessment.

Confidence can move the other way, too (figure below, on the right). Reasoning through a solution that initially looks straightforward may reveal a mistaken assumption or a contradiction. A useful confidence estimate should be able to reflect that change, even when the model still gives the wrong answer. However, standard reasoning models do not necessarily come with this ability: producing a detailed reasoning process does not guarantee that a model can reliably assess and communicate its uncertainty. This is the idea behind our method CALIBER : train a reasoning model to estimate its chance of success before it begins, then assess its particular answer afterwards. On our math benchmark, the calibrated 7B model reduces calibration error by more than half compared with the best single-confidence baseline on this metriic. The key is that the two confidence estimates answer different questions. One confidence score hides two questions Before reasoning, the model has only seen the question. It can recognise the topic and judge whether the problem looks manageable. Its confidence answers: “How likely am I to solve this?”

After reasoning, it has something more specific to assess: the solution it actually produced. Now the question is: “How likely is this answer to be correct?”

These predictions are related, but they serve different purposes. Initial confidence gives an indication of whether the model expects to handle the question successfully. Final confidence helps a user judge whether the resulting answer needs closer scrutiny. A model might often solve this kind of problem and still make a mistake on this attempt. Or it might approach a difficult question cautiously, then find a solution it can check.

CALIBER trains the model to report both estimates in one response: initial confidence, reasoning, an answer, and final confidence. The two numbers can disagree because reasoning gives the model new information to assess. The goal is to make these estimates meaningful enough to support decisions about when to accept an answer, verify it, or seek help. Teaching confidence what to predict To train initial confidence, we let the model try the same question several times. If seven out of ten attempts succeed, 70% becomes the training target. That captures how often the current model can solve the question, before we know which particular attempt it will produce.

Final confidence gets a different target: whether that individual answer is correct. A successful and an unsuccessful attempt at the same question share an initial-confidence target, but receive different final-confidence targets. The figure below shows how this works. In this example, three of four attempts succeed, giving an initial-confidence target of 75%. The fourth attempt produces a wrong answer, so its final-confidence target is 0. The displayed 60% and 20% are the model’s predictions. Training rewards it for moving those predictions closer to their respective targets.

We combine these confidence rewards with a reward for answering correctly. The model is encouraged both to solve the problem and to assess its chances accurately. Recognizing uncertainty about a wrong answer can improve its confidence reward, but it does not earn the reward for a correct solution. The aim is to make confidence more useful while keeping the model focused on getting the answer right. Why saying 70 percent every time is not enough Imagine a model that answers 70% of questions correctly and reports 70% confidence every time. Its confidence matches its overall accuracy perfectly. But if you only have time to check a few answers, those identical scores give you no way to choose.

Now imagine another model with the same overall accuracy. It assigns 90% confidence to half its answers and...