whatmodel.sh / BLOOMZ 7.1B MT
BLOOMZ 7.1B MT
↗ share
+ contribute
BLOOMZ 7.1B MT is an open-weights language model from BigScience, released November 2022. Its published size is 7.07B parameters. Licence: bigscience-bloom-rail-1.0.
Catalogue identity notes
BLOOM 7.1B multitask-finetuned on xP3mt (xP3 plus machine-translated prompts; Muennighoff et al., arXiv 2211.01786); checkpoint bigscience/bloomz-7b1-mt. Not plain BLOOMZ-7b1.
Model information sources
Score within the LMArena (text) comparison set only.
$ how it compares
The LLMs ranked either side of BLOOMZ 7.1B MT, out of 1182 with a score, then more from BigScience.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 732 |  Jais Family 30B 8K Chat | 47±3 | local | ||
| 733 | internlm2-chat-20b-ExPO | 47±2 | local | ||
| 734 | BLOOMZ 7.1B MT | 47±10 | comparison only | ||
| 735 |  Qwen2-VL 7B Instruct | 47±1 | local | ||
| 736 |  DeepSeek R1 Distill Llama 8B | 47±1 | local | ||
| more from BigScience | |||||
| 979 | T0+ (T0p) 11B | 38±9 | comparison only | ||
| 1028 | T0 11B | 35±3 | comparison only | ||
| 1049 | BLOOMZ 176B | 33±2 | comparison only | ||
$ what it's good at
other tests1 not in a task · 58% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CAIL charge prediction, zero-shot open question (accuracy) | 49.8% ✎ | █···█··█···█ beats 2/3 | 58% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/bigscience ↗
$ how the score was worked out · A Comprehensive Evaluation of… 58%
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 |
|---|---|---|
 A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction — authors' own runs | 1 | 58% |
| prior · pull toward the middle | 42% | |
| weighted average | = 47.0 |
$ 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