OpenAI

GPT-6.2 Sol

Intelligence
54.9
Rank 19 of 813 measured models
Output speed
66.2 t/s
Rank 322 of 476 measured models
Context window
1M
Rank 120 of 1420 measured models
Cost per task
$0.564
Rank 122 of 255 measured models

GPT-6.2 Sol (High) is a text AI model from OpenAI, released on Nov 17, 2026, with a context window of 1M tokens. GPT-6.2 Sol (High) scores 54.9 on the Artificial Analysis Intelligence Index, ranking 19th of 813 measured models. The closest models on this index are GPT-6.1 Sol (54.6), Claude Sonnet 5.5 (Default Fallback) (54.5), and Gemini 4 Hydrogen (53.9). With an output speed of 66.2 t/s, it is faster than GPT-6.1 Sol (45 t/s), slower than Claude Sonnet 5.5 (Default Fallback) (147 t/s) and Gemini 4 Hydrogen (164 t/s). Every benchmark side by side: GPT-6.2 Sol (High) vs GPT-6.1 Sol.

Artificial Analysis Indices

High
Intelligence54.9
Rank 19 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 & Accounting54.8
Rank 29 of 283 measured models
Strategy & Ops58.0
Rank 17 of 283 measured models
Legal51.4
Rank 41 of 283 measured models
Healthcare & Medical51.2
Rank 27 of 210 measured models
Engineering58.7
Rank 25 of 281 measured models
Economics54.7
Rank 32 of 289 measured models

Cyber Index

Artificial Analysis · v1
Cyber Index37.0%Rank 21 of 36 measured models
Successes
37.0%
Safety blocks
35.2%
Failures
27.8%
CWE-Bench-AA61.7% (safety blocks)
DeepsecBench-AA49.3% (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