In an earlier open-weight evaluation, multi-turn ASR reached 92.78% against Mistral Large-2.
In an earlier open-weight evaluation, multi-turn ASR reached 92.78% against Mistral Large-2. — This cybersecurity statistic was published by Cisco in May 2026. It covers topics including Large Language Models, Adversarial Attacks, Open Models. The original data appears in Proprietary Problems: How Frontier Closed Models Collapse Under Iterative Pressure. For the full methodology and detailed findings, refer to the original report.
Share or Copy this stat
Frequently Asked Questions
What does this statistic say?
In an earlier open-weight evaluation, multi-turn ASR reached 92.78% against Mistral Large-2. This data was published by Cisco and covers Large Language Models, Adversarial Attacks, Open Models.
Where does this data come from?
This statistic comes from Proprietary Problems: How Frontier Closed Models Collapse Under Iterative Pressure, published by Cisco on May 31, 2026. You can view the original report at https://www.cisco.com/content/dam/cisco-cdc/site/en_us/products/security/proprietary_problems.pdf.
What cybersecurity topics does this cover?
This statistic relates to Large Language Models, Adversarial Attacks, Open Models. Browse more statistics on Large Language Models or from Cisco.