OpenAI

GPT-6.2 Astra

Models.dev
Intelligence
62.1
Rank 3 of 813 measured models
Output speed
48.6 t/s
Rank 407 of 476 measured models
Context window
1M
Rank 120 of 1420 measured models
Cost per task
$4.00
Rank 221 of 255 measured models

GPT-6.2 Astra (Max) is a text AI model from OpenAI, released on Nov 17, 2026, with a context window of 1M tokens. GPT-6.2 Astra (Max) scores 62.1 on the Artificial Analysis Intelligence Index, ranking 3rd of 813 measured models. The closest models on this index are Claude Fable 5.2 (Default Fallback) (64.6), Gemini 4 Neon (61.4), and Gemini 4 Carbon (60.0). With an output speed of 48.6 t/s, it is slower than Claude Fable 5.2 (Default Fallback) (109 t/s), Gemini 4 Neon (105 t/s), and Gemini 4 Carbon (58.3 t/s). Every benchmark side by side: GPT-6.2 Astra (Max) vs Gemini 4 Neon.

Artificial Analysis Indices

Maximum
Intelligence62.1
Rank 3 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 & Accounting60.9
Rank 7 of 283 measured models
Strategy & Ops63.3
Rank 5 of 283 measured models
Legal58.7
Rank 9 of 283 measured models
Healthcare & Medical57.0
Rank 5 of 210 measured models
Engineering66.6
Rank 5 of 281 measured models
Economics61.1
Rank 5 of 289 measured models

Cyber Index

Artificial Analysis · v1
Cyber Index37.3%Rank 20 of 36 measured models
Successes
37.3%
Safety blocks
45.7%
Failures
17.0%
CWE-Bench-AA65.0% (safety blocks)
DeepsecBench-AA46.8% (safety blocks)
CyberGym-E2E-AA0.0% (safety blocks)
Cost per task—

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

Standard Benchmarks

FrontierCode 2.045.4%
Rank 3 of 37 measured models
Terminal-Bench-Science78.1%
Rank 1 of 37 measured models
HLE-Diamond72.2%
Rank 2 of 37 measured models
CritPt v2 (Hard Subset)71.5%
Rank 2 of 33 measured models
AutomationBench-AA77.2%
Rank 3 of 37 measured models
GDP.pdf (all-pass)29.8%
Rank 7 of 37 measured models
FrontierMath Tiers 1–3 (Epoch AI)92.6%
Rank 4 of 82 measured models
FrontierMath Tier 4 (Epoch AI)100.0%
Rank 1 of 69 measured models

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