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.
More from Models
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16
- Google won't publish Argon 4 limits in AI Pro—users compare experiences — Consistent-Text-2662 · 2026-10-16