Levels crossed

Which provider statements say a capability level was crossed, not crossed or not determined?

138 rows, one per model version, domain and level; 9 match the choice below. Grouped by model, newest first.

Gemini 4 Argon Google DeepMind

1 statement · not crossed 1

Other · CCL (Critical Capability Level) · Stated as not crossed
Gemini 4 Argon's performance remains below our CCL threshold.
Google DeepMind · 13 October 2026 · Read the source

GPT-6 Astra OpenAI · 3 September 2026

1 statement · not determined 1

Other · High · Not determined
Astra improves meaningfully over GPT-5.6 Sol on real internal research debugging tasks, scoring 78.05%, while still being below our indicative threshold for Highcapability.
OpenAI · 3 September 2026 · Read the source

Gemini 3.5 Audio Google DeepMind

1 statement · not crossed 1

Other · Tracked or critical capability level (t/ccls) · Stated as not crossed
they did not reach any Tracked or Critical Capability Levels (T/CCLs) outlined in our Frontier Safety Framework .
Google DeepMind · 26 August 2026 · Read the source

Gemini 3.5 Flash-Lite Google DeepMind

1 statement · not determined 1

Other · CCL (Critical Capability Level) · Not determined
Our assessments have shown that, while Gemini 3.5 Flash-Lite excels at agents and coding, it does not have meaningful new capabilities or material increases in performance with respect to the domains outlined in our Frontier Safety Framework compared to Gemini 3.1 Pro; therefore, based on Gemini 3.1 Pro results, we are confident that Gemini 3.5 Flash-Lite is also unlikely to reach any CCLs.
Google DeepMind · 21 July 2026 · Read the source

Gemini 3.5 Transcribe Google DeepMind

1 statement · not determined 1

Other · CCL (Critical Capability Level) · Not determined
Our assessments have shown that none of Gemini 3.5 Translate, Gemini 3.5 Transcribe, or Gemini 3.5 Transcribe Live have meaningful new T/CCL-relevant capabilities or material increases in performance with respect to Frontier Safety compared to Gemini 3.1 Pro and Gemini 3.7 Flash, therefore we are confident that none of them are likely to reach any CCLs.
Google DeepMind · 9 June 2026 · Read the source

Gemini 3.5 Transcribe Live Google DeepMind

1 statement · not determined 1

Other · CCL (Critical Capability Level) · Not determined
Our assessments have shown that none of Gemini 3.5 Translate, Gemini 3.5 Transcribe, or Gemini 3.5 Transcribe Live have meaningful new T/CCL-relevant capabilities or material increases in performance with respect to Frontier Safety compared to Gemini 3.1 Pro and Gemini 3.7 Flash, therefore we are confident that none of them are likely to reach any CCLs.
Google DeepMind · 9 June 2026 · Read the source

Gemini 3.1 Flash-Lite Image Google DeepMind · June 2026

1 statement · not determined 1

Other · CCL (Critical Capability Level) · Not determined
Our assessments have shown that Gemini 3.1 Flash-Lite Image is less capable than Gemini 3.1 Pro, therefore based on Gemini 3.1 Pro, we are confident that that Gemini 3.1 Flash-Lite Image is also unlikely to reach any CCLs.
Google DeepMind · June 2026 · Read the source

Gemini 3.1 Flash Audio Google DeepMind

1 statement · not determined 1

Other · CCL (Critical Capability Level) · Not determined
Our assessments have shown that Gemini 3.1 Flash Audio is less capable than Gemini 3.1 Pro.
Google DeepMind · 15 April 2026 · Read the source

Gemini 3.1 Flash-Lite Google DeepMind

1 statement · not determined 1

Other · CCL (Critical Capability Level) · Not determined
Our assessments have shown that Gemini 3.1 Flash-Lite is less capable than Gemini 3.1 Pro, therefore based on Gemini 3.1 Pro, we are confident that Gemini 3.1 Flash-Lite is also unlikely to reach any CCLs.
Google DeepMind · 3 March 2026 · Read the source

Abbreviations in these level names

CCL: Critical Capability Level: A capability level at which, without safeguards, a model may pose a heightened risk of severe harm.
capability thresholds called “critical capability levels (ccls).” these are capability levels at which, absent mitigation measures, frontier ai models or systems may pose heightened risk of severe harm.
Google DeepMind · Read the source

Not listed: 96 more stored statements that do not, on their own, state a level for one model version (for example a definition of a level, a sentence about another model, or text damaged in our copy of the document).

A row is one model version, one domain and one level. The 138 rows quote 121 different sentences. We count a sentence once by its exact text, even where it fills several rows or appears under several versions. 8 stored rows state a level already listed for the same version and domain under another name or in another sentence; each is listed under that row and not counted again.