/AI4h ago

Claude 4.8 Opus Tops GBA Eval Leaderboard Ahead of GPT-5.5

--0--
Original posts
Quote posts
Original post
Lisan al Gaib@scaling01#980inAI

Claude 4.8 Opus smashes GPT-5.5 and is new SOTA on GBA Eval

On GBA Eval models are used as coding agents to build a working Game Boy Advance emulator from scratch within 24 hours.

3:09 PM · May 31, 2026 · 24.4K Views
Sentiment
Sentiment unavailable for this story.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS10KBOOKMARKS16LIKES108RETWEETS2REPLIES9
Lisan al Gaib@scaling01

Opus 4.8 also progresses much faster than GPT-5.5 on this eval

Lisan al Gaib@scaling01

Claude 4.8 Opus smashes GPT-5.5 and is new SOTA on GBA Eval

On GBA Eval models are used as coding agents to build a working Game Boy Advance emulator from scratch within 24 hours.

4hViews 10KLikes 108Bookmarks 16