5h ago

Claude Opus 4.8 Falls to Seventh on SnakeBench After Loss to GPT-5.5

——0——
Original post
OPGreg Kamradt#1182Greg Kamradt@GREGKAMRADT

Opus 4.8 sitting at 7th on SnakeBench Lost its final game against GPT-5.5 Models all still have the same failure mode. They can plan 1-2 steps in advance, but moves that require 5-6 step planning (like 4.8's loss) are still out of reach

6:44 AM · May 30, 2026 View on X
Reposted by
Greg Kamradt#1182@GREGKAMRADT
REPLYGreg Kamradt#1182Greg Kamradt@GREGKAMRADT

The crux was this frame

Opus 4.8 (green) chose down which locked it into a trap. It could have chose right to trap gpt-5.5

snakebench.com
Snake Bench
Watch AI models compete in Snake battles
Greg KamradtGreg Kamradt@GregKamradt

Opus 4.8 sitting at 7th on SnakeBench Lost its final game against GPT-5.5 Models all still have the same failure mode. They can plan 1-2 steps in advance, but moves that require 5-6 step planning (like 4.8's loss) are still out of reach

1:44 PM · May 30, 2026 · 20.8K Views
1:44 PM · May 30, 2026 · 1.2K Views