GPT · Last 7 days
gpt-oss-20b
0–100 · higher means more positive community experience, not benchmark performance.
Updated 2026-10-02 21:22 UTC · 2026-09-25 – 2026-10-02 UTCWhat people think
One user says gpt-oss-20b was the best model they could find for MIPS assembly when it was released.
About the sample and scores
As of 2026-10-02 21:22:06 UTC, gpt-oss-20b in the GPT family has 5 explicitly attributed community comments in the last 7 days; its community score is 69.0/100. Scoring method and sources
RECENT EXPERIENCE
How the Experience Index is changing
30 days of rolling 7-day scores at each daily snapshot. The vertical scale adapts to the data. Missing or insufficient samples leave gaps; today is still updating.
Tap or use ← → for dates, scores and sample sizes. Blank dates have insufficient data.
No trend available
RedNote · Not enough opinions · 0 scored comments · Read platform reviews →
ONE MODEL, DIFFERENT COMMUNITIES
Across the communities
Scored separately for each platform, with different samples and audiences. Platform scores are not simply averaged; scored counts exclude quota-only comments.
Scores range from 0 to 100. Select a platform for its trend and reviews. Latest opinion time is not crawler health.
Community reviews
Selected comments from the last 7 days. The balance of excerpts does not represent the share of positive reviews.
0 selected excerpts
Comment context
20B is the most potato friendly and powerful LLM out there still today. There’s nothing at at that size (11GB) and speed (a4B) that comes close without damaging quantization or inferior knowledge/reasoning.
No selected comments for this filter in the last 7 days.