Ultramarine 1 Flash
Shares rank 50 of 72 language models by recommenders
Recommended for cheap, capable performance that people say matches GPT-Luna 6 on benchmarks and price, though critics doubt the benchmark claims.
Recommended for cheap, capable performance that people say matches GPT-Luna 6 on benchmarks and price, though critics doubt the benchmark claims.
22 people gave an opinion
- recommend it
- 10
- criticize it
- 12
- approval share
- 45%
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: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 10 people recommend itNeeds 10 or more, met.
- 0.8 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
Performs close to GPT-Luna 6
“for a specialised model, it performs extremely closely in score and price to GPT-Luna 6”
Comment from 17 Oct 2026 in “Ultramarine 1 Flash” “it's open source and is actually cheap to run, while performing the same”
Comment from 17 Oct 2026 in “Ultramarine 1 Flash” Cheap to run
“it's open source and is actually cheap to run, while performing the same”
Comment from 17 Oct 2026 in “Ultramarine 1 Flash” “Price/performance is as advertised in my limited testing.”
Comment from 17 Oct 2026 in “Ultramarine 1 Flash”
What people warn about
Each mark is one comment
Benchmarks look cherrypicked or misleading
“The improvements in other areas might help coding, but aren't that big either, except on their own benchmark.”
Comment from 17 Oct 2026 in “Ultramarine 1 Flash” “They're definitely trying to mislead people into thinking this is something more than it is”
Comment from 17 Oct 2026 in “Ultramarine 1 Flash” “That looks like extreme cherrypicking and doing this speaks against the Ultramarine team.”
Comment from 17 Oct 2026 in “Ultramarine 1 Flash” - Comment from 17 Oct 2026 in “Ultramarine 1 Flash”
- Comment from 17 Oct 2026 in “Ultramarine 1 Flash”
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 |
| Ultramarine 1 FlashThis page | 10 | 12 | 45% | 1 | — | — |
What people said
20 of the 22 comments that mention it, newest first. Each links to the original comment.
“at least disclose # of flops spent or amount of data used”
“Too bad they didn't release model weights”
“Price/performance is as advertised in my limited testing.”
“They're definitely trying to mislead people into thinking this is something more than it is”
“That looks like extreme cherrypicking and doing this speaks against the Ultramarine team.”
“Looks good, but the chached inputs could use a zero more.”
“for a specialised model, it performs extremely closely in score and price to GPT-Luna 6”
“It seems like whatever statistical trick they used also inflated gemini 3.8 to absurd scores as well.”
“Our agent can do work on your machine for you”
“they choose to compare Ultramarine only to models that it's better than on every metric”
“The benchmarks are not ideal.”
“it's open source and is actually cheap to run, while performing the same”
“seems exactly like a skinned glm 5.3 - flash with a few context injection tricks and guardrails”
“this is not Fable-class. This is Luna class. Look at the graphs.”
“Your thing is impressive.”
“it will sorta get the job done but it won't be great at it”
“I signed up, then wait a long. You will be same”
“The improvements in other areas might help coding, but aren't that big either, except on their own benchmark.”
“The model alone looks great (according to benchmarks)”
“this is pretty useful in office”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.