Yhn HealthMedicine first seen 1 d ago, last 27 min ago, peak #4
Memdoor claims five Qwen models beat Fable 5 on hard coding benchmark
Original: Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard
An open-source project called Memdoor reports that a team of five Qwen3.8-27B language models working together outperformed Fable 5 on the LiveCodeBench Hard coding benchmark. The claim, published with the project's workflow examples on GitHub, has drawn attention among developers debating whether coordinated multi-model teams can rival larger frontier systems on difficult programming tasks.
Why now: Developers are debating whether a coordinated team of smaller open models can outperform a leading frontier model on a hard benchmark.
MemdoorQwenFable 5LiveCodeBenchGitHub
Rank over time, top of the chart is #1. 109 snapshots from 1 d ago to 27 min ago.
Evidence
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard · guregodevo · 434
API: https://socialmediatrends-api.osmike.com/v1/trends/4425810