Meta Models Achieve Gold-Medal Results in Five International STEM Olympiads

jack_w_rae · x · 2026-08-07

Meta's research team entered their large language models into five international STEM Olympiads to serve as an uncontaminated benchmark for reasoning capabilities. Three of these were live participations with official grading.

The models achieved gold-medal level results across all five competitions, demonstrating exceptional complex reasoning skills.

Related event: Meta AI Wins Gold in Five STEM Olympiads, Scores Perfect in Physics and Corrects Official Answer(7 posts)→

Original post →

More from Models

• Rabdos Launches Math AI Benchmark; Claude Opus 5 Takes the Lead — AI4Code · 2026-08-07
• Report: ByteDance Discussing 5-Trillion Parameter AI Model — ZeroStateReflex · 2026-08-07
• Local AI Community Booming; Author Bullish on Upcoming GLM 5.3 — andrew_n_carr · 2026-08-07
• TIPO v2 Released: MoE-based Prompt Optimization Model for T2I — bdsqlsz · 2026-08-07
• NVIDIA Open-Sources Full Local Speech Stack: ASR, TTS, and Codecs — ImaginaryRea1ity · 2026-08-07
• Emad Mostaque: Luna reasoning surpasses GPT-5, top-tier AI will be free in 2 years — jdjohnson · 2026-08-07

Models channel →