OpenAI

GPT-6.2 Astra

Intelligence
61.6
Rank 5 of 813 measured models
Output speed
47.5 t/s
Rank 410 of 476 measured models
Context window
1M
Rank 120 of 1420 measured models
Cost per task
$2.52
Rank 201 of 255 measured models

GPT-6.2 Astra (Xhigh) is a text AI model from OpenAI, released on Nov 17, 2026, with a context window of 1M tokens. GPT-6.2 Astra (Xhigh) scores 61.6 on the Artificial Analysis Intelligence Index, ranking 5th of 813 measured models. The closest models on this index are Gemini 4 Neon (61.4), Gemini 4 Carbon (60.0), and Claude Opus 5.5 (Default Fallback) (59.1). With an output speed of 47.5 t/s, it is slower than Gemini 4 Neon (105 t/s), Gemini 4 Carbon (58.3 t/s), and Claude Opus 5.5 (Default Fallback) (113 t/s). Every benchmark side by side: GPT-6.2 Astra (Xhigh) vs Gemini 4 Neon.

Artificial Analysis Indices

Extra high
Intelligence61.6
Rank 5 of 813 measured models

Reasoning levels

Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Cost per task

Capability indexes

Performance in specific industries, measured by Artificial Analysis
Finance & Accounting60.2
Rank 8 of 283 measured models
Strategy & Ops62.0
Rank 7 of 283 measured models
Legal56.9
Rank 14 of 283 measured models
Healthcare & Medical54.9
Rank 9 of 210 measured models
Engineering65.1
Rank 8 of 281 measured models
Economics59.0
Rank 12 of 289 measured models

Cyber Index

Artificial Analysis · v1
Cyber Index40.6%Rank 17 of 36 measured models
Successes
40.6%
Safety blocks
41.4%
Failures
17.9%
CWE-Bench-AA69.2%
DeepsecBench-AA52.7% (safety blocks)
CyberGym-E2E-AA0.0% (safety blocks)
Cost per task—

* The model or provider declined some tasks on safety grounds.

Models at a similar level

The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy