whatmodel.sh / MedReason-8B

MedReason-8B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

MedReason-8B is an open-weights language model from UCSC VLAA, released April 2025. Its published size is 8.03B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo UCSC-VLAA/MedReason-8B @2730640: licence tag apache-2.0. 8,030,261,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-04: month the maker's Hugging Face repo was created (createdAt 2025-04-01).

34.2±5.2#813 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of MedReason-8B, out of 1132 with a score.

#modelscorewhereRAMreleased
978Granite 3.1 3B-A800M Instruct IBM35±2local~3.6GB2024-12
979Vicuna 7B v1.5 16K LMSYS34±2local~5.8GB2023-07
980MedReason-8B UCSC VLAA34±5local~18GB2025-04
981Llama 2 13B (base) Meta34±1local~9.3GB2023-07
982GPT-3.5 text-davinci-003 OpenAI34±3comparison only2022-11

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 88% of its score
testresultvs the others in its rundifficultycountswhy
BRIDGE clinical text, zero-shot average (87 tasks)18.2% ✎▁▁▁▁▃▂▂▃▄▆█▃ beats 7/97hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 88%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~16.06 GB · from huggingface.co/UCSC-VLAA (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='UCSC-VLAA/MedReason-8B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/UCSC-VLAA ↗

$ how the score was worked out · BRIDGE Medical Leaderboard (H… 88%

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

sourceresultsshare of the scorelicence
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 88%MIT
prior · pull toward the middle▇▇▇▇ 12%
weighted average= 34.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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