whatmodel.sh / decision / KnowLine 35B-A3B Gen1
KnowLine 35B-A3B Gen1
↗ share
+ contribute
KnowLine 35B-A3B Gen1 is an open-weights decision model from PelaAI, released 12 October 2026. Its published size is 35.95B parameters. Licence: apache-2.0.
Catalogue identity notes
Exact Decision Index tested engine knowline-35b-a3b-gen1; reported model KnowLine 35B-A3B Gen1. Type: LoRA; technique: autoregressive. Comparison entry; no current run command, API price or speed inferred from the benchmark. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.
Model information sources
Release date ↗ · Weights licence ↗ · Parameter count ↗
Publisher parameter count; includes the served backbone, not just adapter size.
$ how it compares
The decision models ranked either side of KnowLine 35B-A3B Gen1, out of 357 with a score, then more from PelaAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 68 |  OneJev1.6-9B | 64±1 | model files | ||
| 69 |  JEV-27B-VL | 64±4 | model files | ||
| 70 | KnowLine 35B-A3B Gen1 | 64±4 | model files | ||
| 71 | jev-vision-27b | 64±4 | model files | ||
| 72 |  Xor 26B-A4B v1.2 | 63±1 | model files | ||
| more from PelaAI | |||||
| 5 | KnowLine 31B Gen1 | 73±2 | model files | ||
| 12 | KnowLine 35B-A3B Gen1.5 | 71±2 | model files | ||
| 22 | KnowLine 26B-A4B Gen2.5 | 69±2 | model files | ||
see all decision models · find the ones that fit your machine
$ what it's good at
vision▁·▃▂▃▃▇▄▄█▄▃ #30 of 79 · 95% of its score · 12 tests
Beats StartLux-Decision v1.1 9B, RSI-Jev v6.1 VL 27B (effort auto), StartLux-Decision v1.1 4B here, though they rank higher overall. Trails Clef-flash, Perplexity Decider Flash v1.2 (4B), Mercury Decide (free endpoint) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted | 79.9900 points ✎ | ▁·▁▁▃▁▄▄▃▅█▂ beats 40/61 | 12% |
| Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted | 44.2400 points ✎ | ▁▁▅▁▄▁▄█▄▃▇▇ beats 51/61 | 11% |
| Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted | 79.2500 points ✎ | ▁·▁▁▁▁·▂▁▃▅█ beats 28/61 | 10% |
| Decision Index Vision 0.4: private same skills (points) | 63.5900 points ✎ | ▁▁▃▃▁▂▄▆▃▃▅█ beats 42/61 | 10% |
| Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted | 47.7300 points ✎ | ▆▃▃▆▄▄▇██▃▆▆ beats 49/61 | 8.8% |
| Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted | 70.8700 points ✎ | ▁·▂▂▁▃▃▅▅▃▃█ beats 46/61 | 8.0% |
| Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted | 79.4500 points ✎ | ▂▁▁▁▁▃▁▅▅▆██ beats 47/61 | 7.8% |
| Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted | 99.4500 points ✎ | ▁·▁▂▁▁▃▁▂▂▅█ beats 61/61 | 6.2% |
4 more tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted | 29.6100 points ✎ | ▂▄▇▆█▄▄▇▂··▁ beats 38/61 | 6.2% |
| Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted | 56.8300 points ✎ | ▁···▁▂▂▂█▄▂▃ beats 39/61 | 5.9% |
| Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted | 76.0400 points ✎ | ▁▁▁▁▂▁▁▁▄█▃▃ beats 37/61 | 4.7% |
| Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted | 92.7200 points ✎ | ▁··▁▁▁▁▁▂▄█▁ beats 52/61 | 3.4% |
$ where to run it
Download model files ↗
Published model files verified. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. A local run command and hardware requirements have not been verified for this entry. Source · checked 2026-10-31.
Model repository and documentation: huggingface.co/PelaAI ↗
$ how the score was worked out · Decision Index Vision 0.4 95%
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 |
|---|---|---|
 Decision Index Vision 0.4 · submitted; independent execution unverified | 12 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 63.6 |
$ 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