OpenAI's new model GPT 6.2 Astra suspected of being in gray testing, internal model engineering benchmark score improves 47.3%

Skip 6.1 Astra? New OpenAI model exposed, engineering benchmark score jumps 47% Phoenix Tech Download the app for exclusive early access November 04, 2026 13:35:48 From Beijing Updated November 04, 2026 13:12:16

Phoenix Tech News, Beijing time, November 4 — OpenAI's next-generation flagship model, GPT 6.2 Astra, is suspected to have entered small-scale gray-release testing. Recently, multiple overseas developers spotted a new model identifier named "gpt-6.2-astra" in Codex usage statistics, with some accounts showing it accounting for 19.8% of calls. At the same time, OpenAI officially published the results of an as-yet-unreleased internal model on a 3D engineering design benchmark, showing an improvement of about 47.3% over the current GPT 6 Astra, fueling speculation that a new-generation model is about to be released.

According to tech media outlet TestingCatalog, since October 31, the usage analysis pages of some Codex users have shown a separate record for GPT 6.2 Astra, but the model selection interface still displays GPT 6 Astra.

Screenshots posted by X platform blogger Token Gremlin show that about 19.8% of one account's model calls were counted under GPT 6.2 Astra, while about 80% were still attributed to GPT 6 Astra. The call ratios differ across users' screenshots, leading some developers to speculate that OpenAI may be conducting A/B testing through backend request routing.

In addition, on November 3, overseas model-tracking account LuminaBench claimed that two new identifiers, "rc-ada-or-vm" and "rc-ada-sh-vm," briefly appeared in the OpenAI API model list before disappearing. Some developers speculate that these codenames may be related to release candidate versions of the new model, but there is currently no evidence to confirm that they correspond to GPT 6.2 Astra.

It is worth noting that OpenAI has not officially announced GPT 6.2 Astra, nor confirmed the aforementioned gray-release testing or the release timing of the new model. Some model demo videos circulating on social platforms are also disputed as to their authenticity and cannot serve as evidence that the new model's performance has been verified.

Just as the gray-test rumors continued to ferment, OpenAI published a technical blog post titled "Accelerating Engineering Development for the Physical World" on November 3, disclosing the latest progress of AI models in mechanical design, electronic engineering, and physical manufacturing.

Among them, the most closely watched was a set of test results for an as-yet-unreleased model.

In the BenchCAD 2.0 engineering benchmark, the current GPT 6 Astra scored an average of 0.594 under the highest reasoning setting, while a model OpenAI calls a "newer internal model" reached an average score of 0.875, a relative improvement of about 47.3%.

BenchCAD 2.0 mainly evaluates a model's ability to reconstruct 3D mechanical parts and assemblies and to identify circuit board connection relationships. OpenAI believes this result preliminarily indicates that the new-generation model is expected to further improve the iteration efficiency of professional engineering design.

However, OpenAI did not disclose the official name of this internal model, nor explain whether it is the GPT 6.2 Astra rumored recently. The above results are specific engineering benchmark test results and cannot yet directly represent the overall success rate of real manufacturing tasks.

In addition to publishing the model's benchmark scores, OpenAI also demonstrated a case in which GPT 6 Astra participated in physical hardware design.

According to the official introduction, two engineers used GPT 6 Astra to complete the design of a portable AI device in less than a week. The device can interact with Codex via voice, and the model participated in the design of the enclosure structure, internal mechanical components, PCB circuit boards, electronic components, user interface, and firmware software.

Throughout the design process, the engineers did not directly manually modify the designs generated by the model. Subsequently, a contract manufacturer produced a small batch of physical prototypes in less than a month.

But OpenAI also acknowledged that turning designs into manufacturable products still requires multiple rounds of manual review and iteration. GPT 6 Astra cannot yet always accurately account for production process constraints, manufacturing tolerances, and assembly details.

OpenAI also disclosed that since February this year, the number of tokens consumed by its hardware team using AI models has grown 23-fold. Codex and ChatGPT are being used for computer-aided design, manufacturing drawing generation, engineering simulation, and design review.

On external cooperation, OpenAI announced a new research collaboration with Mazda to explore the use of AI to assist automotive aerodynamics and crash safety design. GPT 6 Astra can generate different front-end geometric shapes and combine airflow simulation to help engineers evaluate design options.

Mazda chief engineer Akihiro Nakata said that by using AI to explore and simulate dozens of design variants, engineers can more clearly understand which styling features affect aerodynamic performance and in which areas designers have greater styling freedom.

OpenAI has also expanded its cooperation with IndyCar team Chip Ganassi Racing, attempting to convert 3D scan data of existing components into editable CAD models and 2D manufacturing drawings to reduce engineers' repetitive work in reverse modeling and prototype development.

From the new model identifier appearing in the Codex backend to the officially published engineering benchmark scores of the internal model, a series of recent information shows that OpenAI is continuing to advance large models' programming, computer operation, and physical engineering design capabilities.

However, whether GPT 6.2 Astra has officially entered gray testing, whether the internal new model corresponds to this version, and when the new model will be released all still await official confirmation from OpenAI. (Editor/Yu Lei)

For more first-hand news, please download the Phoenix News app and subscribe to Phoenix Tech. For in-depth reports, search "Phoenix Tech" on WeChat.