GPT 5.5 + Claude 4.8 Ensemble Powered AIRA₃'s 8th-Ranked Gold Medal Kaggle Entry

AIatMeta · x · 2026-09-06

Meta details the model combinations behind AIRA₃'s live Kaggle run: the 8th-ranked gold medal entry was an ensemble of GPT 5.5 (with OpenCode) + Claude 4.8 (with ClaudeCode).

Post-hoc submissions, graded externally on the same private test set, showed Muse Spark 1.2 (with MuseCode) also hitting gold, while Muse Spark 1.1 and GLM 5.2 (both with OpenCode) reached silver — suggesting the system is robust across underlying models.

Related event: Meta's AIRA₃ Coordinates Long-Running Agents to Win Kaggle Gold(3 posts)→

Original post →

More from coding & agent

coding & agent channel →