๐ArXiv AIโขStalecollected in 17h
Independent GPT-OSS-20B Benchmark Reproduction

๐กFirst independent repro of OpenAI gpt-oss-20b agent benchmarks + open harness
โก 30-Second TL;DR
What Changed
Reverse-engineered tools from gpt-oss-20b training distribution via prompts
Why It Matters
Validates OpenAI's gpt-oss-20b agent claims independently, boosting trust in published benchmarks. Provides open tools for community agent development and evaluation.
What To Do Next
Clone https://github.com/borislavmavrin/harmonyagent.git and test gpt-oss-20b on SWE-bench.
Who should care:Researchers & Academics
Key Points
- โขReverse-engineered tools from gpt-oss-20b training distribution via prompts
- โขBuilt harmonyagent GitHub repo for native message encoding
- โขReproduced OpenAI scores: SWE Verified HIGH 60.4% (pub. 60.7%), MEDIUM 53.3% (53.2%)
- โขAchieved 91.7% on AIME25 with tools (pub. 90.4%)
๐ฐ
Weekly AI Recap
Read this week's curated digest of top AI events โ
๐Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: ArXiv AI โ