Checked fact 264324 Oct 2026Research

With outcome-based reinforcement learning, Chain-of-Thought faithfulness first rose substantially, then plateaued at 28% on MMLU and 20% on GPQA, per Anthropic.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

Outcome-based RL initially increases Chain-of-Thought faithfulness substantially, but the improvement plateaus at 28% on MMLU and 20% on GPQA.

What the source said when we opened it, on 24 Oct 2026.

The source

Reasoning models don't always say what they think
Anthropic · 2025-04-03

Open the source archived copy

Checked

Checked by the notis newsroom on 24 Oct 2026, against the source above.

In the story

Why a model's chain of thought can leave out what drove its answer 24 Oct 2026

Cite this fact

Short permanent address

In a sentence

“With outcome-based reinforcement learning, Chain-of-Thought faithfulness first rose substantially, then plateaued at 28% on MMLU and 20% on GPQA, per Anthropic.” ai notis, checked 24 Oct 2026. Source: Reasoning models don't always say what they think (Anthropic). https://ainotis.com/c/2643

As a reference (APA style)

ai notis. (2026, October 24). With outcome-based reinforcement learning, Chain-of-Thought faithfulness first rose substantially, then plateaued at 28% on MMLU and 20% on GPQA, per Anthropic [Checked claim 2643]. ai notis. https://ainotis.com/c/2643

Anyone may quote this address. It does not change; if we correct the story, this page says so.