whatmodel.sh / decision / d1.1 (hosted)
d1.1 (hosted)
↗ share
+ contribute
d1.1 (hosted) is a closed-weights decision model from Liquid AI. Licence: proprietary.
Catalogue identity notes
Exact named native decision endpoint liquid/d1.1; reported returned version liquid/d1.1-20261027. Kept separate from d1, d1-ultra and downloadable small d1 variants. Hosted service snapshot, not immutable weights.
$ how it compares
The decision models ranked either side of d1.1 (hosted), out of 357 with a score, then more from Liquid AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 30 | OneShot 27B | 68±2 | model files | ||
| 31 |  Matilda Decision v1 | 68±2 | model files | ||
| 32 | d1.1 (hosted) | 68±2 | api price unknown | ||
| 33 | VisionJEV 1.0.0 (27B) | 68±1 | model files | ||
| 34 |  RBDash-Decision v0.2 | 68±4 | model files | ||
| more from Liquid AI | |||||
| 21 | d1-ultra | 69±2 | api price unknown | ||
| 61 | d1 (hosted) | 65±1 | api price unknown | ||
| 198 | LiquidAI d1-3B | 51±1 | model files | ||
see all decision models · find the ones that fit your machine
$ what it's good at
retrieval & classification▁▁▁·▁▁▁▁▃▃█▅ #60 of 258 · 15% of its score · 6 tests
Beats AutoTrust-JEV-27B v1.1 here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, Standard One 8B SH (v4), StartLux-Decision v1.1 2B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| System One Bench: MIRACL pairwise (Arabic) | 89.5% ✎ | ▂···▁··▃▄▂█▇ beats 16/29 | 5.1% |
| System One Bench: MASSIVE intent (Arabic) | 88.0% ✎ | ▄·▁·▁▃▃▃█▄▇▇ beats 20/29 | 4.3% |
| System One Bench: MIRACL rerank (Arabic) | 88.5% ✎ | ▁▂·▁▁·▂·▄▄█▇ beats 20/29 | 2.9% |
| System One Bench: MASSIVE scenario (Arabic) | 73.0% ✎ | ▃▁·▄▃▂█▂▁▁·▃ beats 20/29 | 2.1% |
| System One Bench: AG News (English) | 90.5% ✎ | ▁···▅▁▅▂▆█▂▅ beats 20/29 | 0.6% |
| System One Bench: Banking77 (English) | 87.0% ✎ | █▅▆█▅▃▃▃···▂ beats 9/26 | 0.0% |
language understanding▂▂▂▃▂▅▆▃█▆▄▃ #17 of 256 · 14% of its score · 9 tests
Beats KnowLine 31B Gen1, Ainvest-Decision-27B v1.0, WeMM-JEV-27B here, though they rank higher overall. Trails Clef-omni, Clef, Darwin-27B-ZTC here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| System One Bench: BoolQ (English) | 92.0% ✎ | ▁▁▁▃·▁▃▃▇▇█▅ beats 26/29 | 3.6% |
| System One Bench: OSACT4 offensive (Arabic) | 92.5% ✎ | ▁······▁▃█▇▄ beats 22/29 | 2.9% |
| System One Bench: SST-5 (English) | 60.0% ✎ | ▃·▁▁▃·▇▄▄▄█▅ beats 23/29 | 2.3% |
| System One Bench: SST-2 (English) | 98.0% ✎ | ▁·▃▁▂▂▃▅█·▂▃ beats 29/29 | 2.1% |
| System One Bench: XNLI Arabic (Arabic) | 79.3% ✎ | ▄▁▃▁▄▇█▅▃▁·▃ beats 23/29 | 1.1% |
| System One Bench: XNLI French (French) | 83.3% ✎ | ▂▅·▁▁▅▅█▃▁·▃ beats 21/29 | 0.9% |
| System One Bench: Tweet sentiment (Arabic) | 72.5% ✎ | ▁······▁▁▄█▄ beats 23/29 | 0.9% |
| System One Bench: XNLI English (English) | 90.0% ✎ | ▃·▁·▃▇█▄█▃▃▁ beats 19/29 | 0.3% |
1 more test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| System One Bench: DAIR Emotion (English) | 60.5% ✎ | ██▃·····▁··▁ beats 23/29 | 0.0% |
knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #43 of 263 * · 22% of its score · 1 test
Beats vera-large, OneJev1.6-27B, baselabs elephant-1 (9B) here, though they rank higher overall. Trails Solar Decide, Clef-omni, GPT-6 Luna Decisions here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Etsabary · 1342 text decisions | 77.8% ✎ | ▁··▂·▃▅▁▃▃▂█ beats 15/24 | 22% |
vision▁·▃▂▃▃▇▄▄█▄▃ #2 of 79 · 42% of its score · 6 tests
Beats Fastino GLiDE 1.2, StartLux-Decision v1.1 27B, vLLM-SR d3-ultra (Decision 3.0, 27B) here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Etsabary · 200 image decisions | 72.0% ✎ | ▂▂··▂▃▂·█▃▂▂ beats 9/14 | 16% |
| System One Bench: Image object count | 91.5% ✎ | ▃····▃█▃▅·█▃ beats 6/11 | 5.8% |
| System One Bench: Arabic sentiment screenshot | 61.0% ✎ | ▄··▄··▂···▆█ beats 7/11 | 5.8% |
| System One Bench: SST-2 screenshot | 96.5% ✎ | █···███·█·▄▄ beats 10/11 | 5.1% |
| System One Bench: Visual yes/no questions | 89.5% ✎ | ▂······▃█▃·▃ beats 10/11 | 5.1% |
| System One Bench: Oxford pets classification | 90.5% ✎ | ███·█▄▄·▄··▄ beats 10/11 | 4.2% |
workflows▁▁▁▂▁▂▂▆█▄▁▁ #32 of 114 * · 4.9% of its score · 1 test
Trails StartLux-Decision v1.1 2B, xor (DecisionBench 679decd4), openjev-sglang (DecisionBench 1355db6a) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| System One Bench: Typed decisions (English) | 72.0% ✎ | ▁▁·▁▁▁▅▄▇██▁ beats 17/29 | 4.9% |
$ where to run it
Through an API
api · OpenRouter · price unknown · openrouter.ai ↗
Model repository and documentation: openrouter.ai ↗
$ how the score was worked out · System One Bench (Ali Alhashi… 60%, Etsabary · decision benchmarks 39%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 System One Bench (Ali Alhashimi) | 21 | 60% |
| Etsabary · decision benchmarks | 2 | 39% |
| prior · pull toward the middle | 1% | |
| weighted average | = 68.1 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json