Compare GPT OSS 20B and GPT-5, both from OpenAI, in 1 community votes, gpt oss 20b wins 100% of head-to-head duels, context windows of 131K vs 400K, tested across 47 shared challenges. Updated February 2026.
In 1 community votes, GPT OSS 20B wins 100% of head-to-head duels. Based on blind community voting from the RIVAL open dataset of 1+ human preference judgments for this pair.
47 challenges
Tests an AI's ability to make educated estimates based on technical knowledge
Here’s a back‑of‑the‑envelope estimate using standard LM training-compute heuristics.
Answer
This is a coarse estimate; the exact number depends on details like sequence length, activation checkpointing, implementation efficiency, and the precise token count.
Tests an AI's ability to understand game rules and strategy
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
1
Reason: If each of the 3 brothers has 2 sisters, there are exactly 2 girls in the family. One is Sally, so she has 1 sister.
Tests an AI's understanding of number representation
Tests an AI's randomness and creativity
Tests an AI's ability to generate vector graphics
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Tests an AI's humor and creative writing ability
Tests an AI's ability to simulate personalities and predict future trends
Tests an AI's humor and understanding of current events
Tests an AI's ability to write in distinct character voices
Tests an AI's ability to generate a complete, working landing page
