WHAT NEW IN X11.06 FRI

AI collections from X · 23 collections · 70,791 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 13 hours ago
gpt-6IMAGE

BridgeBench: GPT-6.1 Sol scores just 3 points above GPT-6 Sol

BridgeBench results show GPT-6.1 Sol scoring 3 points higher than GPT-6 Sol but 82 points behind GPT-6 Astra, which the benchmark suggests may indicate benchmaxing on the lab's own tests.

Bridgebench
@bridgebenchArchived 2026.09.30Originally posted 2026.09.30
BridgeBench: GPT-6.1 Sol scores just 3 points above GPT-6 Sol
Bridgebench @bridgebenchOriginally posted 2026.09.30
Open original on X

GPT 6.1 Sol is now on BridgeBench. OpenAI is calling it "near-Astra intelligence." Our results: 3 points better than GPT 6 Sol. 82 points behind GPT 6 Astra. When a model jumps on the lab's own benchmarks but barely moves on independent ones, that's usually a sign of benchmaxing.

x.com/bridgebench/status/2105040913949159914Archived 2026.09.30 10:15
Open original on X