Matching posts

Matching terms are highlighted

POST

Weekly open-source roundup: V4.1 Flash beats GPT-5.6 Sol on Terminal-Bench 4.0 at 20x lower cost

…cosystem roundup says DeepSeek-V4.1-Flash beats GPT-5.6 Sol on Terminal-Bench 4.0 at 20x lower cost, al…

deepseek-v4.1@LeaderX_btc　Filed in No.020

3 days agoCopy original

PHP2Shell: Gemini 4 Argon and GPT-5.6 Sol independently reproduce PHP exploit

Security firm Calif used GPT-5.6 Sol and Wiz used Gemini 4 Argon to independentl…

gemini-4@joho_no_todai　Filed in No.008

3 days agoCopy original

POST

Soliciting impressions of DeepSeek V4.1 Flash: does it beat GPT-5.6 Sol in coding?

…4.1 Flash, specifically whether it really beats GPT-5.6 Sol in coding and whether the reasoning modes d…

deepseek-v4.1@deweytn　Filed in No.020

3 days agoCopy original

POST

Gemini 4 Argon and GPT-5.6 Sol found decade-old PHP RCE flaws

Three security firms independently used GPT-5.6 Sol and Gemini 4 Argon to uncover two CVSS 9.2 …

gemini-4@joho_no_todai　Filed in No.008

6 days agoCopy original

POST

Critical PHP flaws found by GPT-5.6 Sol and Gemini 4 Argon

…ing remote server takeover, found by Calif with GPT-5.6 Sol and by Wiz with help from Gemini 4 Argon af…

gemini-4@vision_ia　Filed in No.008

6 days agoCopy original

20-year-old PHP flaws found with Gemini 4 Argon and GPT-5.6 Sol

…tedly helped find them using Gemini 4 Argon and GPT-5.6 Sol.

gemini-4@falsaif　Filed in No.008

5 days agoCopy original

POST

Community eval: DeepSeek V4.1 Flash 1017 roughly matches GPT-5.6 Sol xhigh

…epSeek V4.1 Flash 1017 as roughly comparable to GPT-5.6 Sol at xhigh effort.

deepseek-v4.1@SongyuKite　Filed in No.020

7 days agoCopy original

POST

Community eval: DeepSeek V4.1 Flash 1017 roughly matches GPT-5.6 Sol xhigh

…ng deepseek-v4.1-flash-1017 roughly on par with GPT-5.6 Sol xhigh, noting it was run inside DeepSeek Ha…

deepseek-v4.1@qqa16803　Filed in No.020

6 days agoCopy original

POST

PHP security bugs found by GPT-5.6 Sol, with GPT-6 Astra cited as stronger

…ys these PHP security issues were discovered by GPT-5.6 Sol, which is no longer OpenAI's frontier publi…

gpt-6@maxifirtman　Filed in No.001

7 days agoCopy original

GPT-5.6 Sol and Gemini 4 Argon helped find decade-old PHP flaws

… back over a decade were exposed, with OpenAI's GPT-5.6 Sol and Google's Gemini 4 Argon helping researc…

gemini-4@Graham_dePenros　Filed in No.008

6 days agoCopy original

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.