From 40683a76712c29c39f7b152beb1b7a7f3c077e85 Mon Sep 17 00:00:00 2001
From: connerlambden <conner@connerpro.com>
Date: Thu, 4 Jun 2026 22:33:08 -0600
Subject: [PATCH] Add BGPT REFUTE benchmark

---
 README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/README.md b/README.md
index aa3bb89e3..e29aa64f7 100644
--- a/README.md
+++ b/README.md
@@ -215,3 +215,8 @@ We thank EleutherAI for their work on the [lm-evaluation harness](https://github
   year = 2022,
 }
 ```
+
+
+## Benchmarks
+
+- [REFUTE](https://huggingface.co/datasets/BGPT-OFFICIAL/refute) — Scientific critique & epistemic calibration (Apache-2.0). [Leaderboard](https://huggingface.co/spaces/BGPT-OFFICIAL/refute-leaderboard) · [Report](https://huggingface.co/datasets/BGPT-OFFICIAL/refute/blob/main/TECHNICAL_REPORT.md) · [Integrations](https://huggingface.co/datasets/BGPT-OFFICIAL/refute/tree/main/integrations)