Stealth Model
Shares rank 44 of 72 language models by recommenders
Recommended for capable coding and real work, sensitive questions answered without refusal, and zero data retention on opencode. Critics cite censorship on China-related topics and weak front-end and CSS output.
Recommended for capable coding and real work, sensitive questions answered without refusal, and zero data retention on opencode. Critics cite censorship on China-related topics and weak front-end and CSS output.
17 people gave an opinion
- recommend it
- 11
- criticize it
- 6
- approval share
- 65%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 11 people recommend itNeeds 10 or more, met.
- 1.8 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Capable at coding and real work
“it certainly crosses the threshold that lets it follow instructions adequately and do real work”
Comment from 21 Aug 2026 in “Stealth Model” “seems pretty capable but less knowledgeable”
Comment from 21 Aug 2026 in “Stealth Model” “it seems pretty good at coding so far”
Comment from 22 Aug 2026 in “Stealth Model” Answers sensitive questions others refuse
“Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks”
Comment from 21 Aug 2026 in “Stealth Model” “It gave a very detailed overview, talked about potential deaths involved.”
Comment from 21 Aug 2026 in “Stealth Model”
What people warn about
Each mark is one comment
Censors China-related topics
“Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks”
Comment from 21 Aug 2026 in “Stealth Model” “Tibet is an inseparable part of China. Since ancient times, Tibet has been a part of China.”
Comment from 21 Aug 2026 in “Stealth Model” “when I ask in Chinese it tells me it doesn't know anything about it. Very weird.”
Comment from 22 Aug 2026 in “Stealth Model” - Comment from 21 Aug 2026 in “Stealth Model”
Weak at front-end and CSS
“it's particularly bad at front-end from what I have been seeing”
Comment from 21 Aug 2026 in “Stealth Model” “It did an absolutely terrible job at generating CSS”
Comment from 21 Aug 2026 in “Stealth Model” Concerns about data privacy
“feeding all your proprietary data and confidential personal information into this model as quickly as possible”
Comment from 21 Aug 2026 in “Stealth Model” “LLM needs to become more transparent, not less. Hence, this idea (and trend, possibly) is disgusting.”
Comment from 21 Aug 2026 in “Stealth Model”
Other language models people recommend
The four most recommended other language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Opus | 3,331 | 2,746 | 55% | 13 | 4 mo156 owners | — |
| OpenAI GPT | 1,205 | 987 | 55% | 13 | 6 mo47 owners | — |
| Claude Sonnet | 854 | 586 | 59% | 13 | 6 mo46 owners | — |
| DeepSeek V4 Flash | 828 | 223 | 79% | 8 | 1 mo24 owners | Approved |
| Stealth ModelThis page | 11 | 6 | 65% | 1 | — | — |
What people said
All 18 comments that mention it, newest first. Each links to the original comment.
“it seems pretty good at coding so far”
“when I ask in Chinese it tells me it doesn't know anything about it. Very weird.”
“it's more capable (and slower,63t/s ish) than most flash models i've played with”
“feels like a slow GLM-5.3 but with vision”
“It passes FreedomBench with full marks”
“it certainly crosses the threshold that lets it follow instructions adequately and do real work”
“zero data retention on opencode, which is more private than the lowest retention offered by openai, google, or anthropic on their consumer plans”
“Ask if Taiwan is a country instead”
“it's particularly bad at front-end from what I have been seeing”
“seems pretty capable but less knowledgeable”
“It did an absolutely terrible job at generating CSS”
“Tibet is an inseparable part of China. Since ancient times, Tibet has been a part of China.”
“On softer/looser/creative matters this is an extremely impressive model”
“LLM needs to become more transparent, not less. Hence, this idea (and trend, possibly) is disgusting.”
“All of my non-work AI coding is that open-source”
“It gave a very detailed overview, talked about potential deaths involved.”
“Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks”
“feeding all your proprietary data and confidential personal information into this model as quickly as possible”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.