gpt-6POST
GPT-6 Astra scores 65.7% on Terminal-bench Science
Astra leads second-place Claude Fable 5.1 by 31.4 points, no other model clears 25%, and 12 of 24 models score 4.3% or lower.
Derya Unutmaz, MD
@DeryaTR_Archived 2026.09.21Originally posted 2026.09.20
Derya Unutmaz, MD @DeryaTR_Originally posted 2026.09.20
This is an insane jump by GPT-6 Astra in Terminal-bench Science! “GPT-6 Astra takes the lead, scoring 65.7%. That’s 31.4 points ahead of the second-place model, Claude Fable 5.1 (34.3%). No other model clears 25%, and 12 of 24 models score 4.3% or lower” Incredible!
This post quotes another post: x.com/valsai/status/2098553038646735233
x.com/deryatr_/status/2101485267479666922Archived 2026.09.21 10:13