BigCodeBench

Search everything

Mentions · 7d0
Mentions · 30d0
All mentions2
First seenSep 2, 2026
Last mentionedOct 7, 2026

Timeline

2 articles · newest first

MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination

MARGIN calibrates multi-model confidence at runtime and lifts answer-selection accuracy by up to 14 points.

Hugging Face daily papersOct 7, 20:00 UTC · Oct 7, 2026AI research1 · 1 read

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

A 400-task BigCodeBench evaluation shows frontier LLMs widely over-edit code; a preservation instruction cuts excess edits and raises Pass@1 by 2.3 points.

Hugging Face daily papersSep 2, 20:00 UTC · Sep 2, 2026AI research2

Appears with

GPT-5.5ai model · 1

Entities are extracted by the model from each article. First seen Sep 2, 2026, last mentioned Oct 7, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.