---
id: "entity-chatgpt-5-4"
type: "entity"
entityType: "product"
canonicalName: "ChatGPT 5.4"
aliases: ["GPT-5.4"]
source_timestamps: ["00:00:00"]
tags: ["llm", "competitor"]
related: ["concept-model-self-review-bias"]
sources: ["s12-opus-47"]
sourceVaultSlug: "s12-opus-47"
originDay: 12
---
# ChatGPT 5.4

## Profile

[[entity-openai-d12|OpenAI]]'s frontier model (per the speaker), used as a benchmark against [[entity-claude-opus-4-7-d12|Opus 4.7]].

## Strengths (per the speaker)

- Excels in **web research**.
- Excels in **terminal execution**.

## Weaknesses (per the speaker)

- Trails Opus 4.7 in [[concept-agentic-persistence|agentic persistence]].
- Trails in **complex knowledge work**.

## Self-Review Behavior

Exhibits an **underselling** bias — grades own work harshly (3.1/5) and surfaces own errors transparently. Inverse of [[entity-claude-opus-4-7-d12|Opus 4.7]]'s overselling bias. See [[concept-model-self-review-bias]] and [[quote-oversell-undersell]].

Notably, GPT-5.4 graded Opus 4.7's work much more strictly than Opus graded itself.

## External Validation

No exact match for 'ChatGPT 5.4' in public records. Closest: OpenAI's GPT-5 High (~55% SWE-bench Verified, 23.3% Pro — https://platform.openai.com/docs/models/gpt-5). Trails in persistence per the video but unverified.

## Cross-References

- Maker: [[entity-openai-d12]]
- Concept: [[concept-model-self-review-bias]]
- Quote: [[quote-oversell-undersell]]
- Framework: [[framework-hex-eval]]