Enabling two settings tripled our scores on the ARC-AGI-3 benchmark
tedsanders
23 points
0 comments
July 29, 2026
Related Discussions
Found 5 related stories in 50.6ms across 3,260 title embeddings via pgvector HNSW
- ARC-AGI Leaderboard rzk · 168 pts · July 25, 2026 · 48% similar
- Advancing the price-performance frontier with GPT‑5.6 tedsanders · 541 pts · July 30, 2026 · 48% similar
- Altman: GPT-5.6 is 54% more token efficient on agentic coding Topfi · 13 pts · July 09, 2026 · 46% similar
- Anthropic is subsidizing our AI coding at 13x. How long will it last? bassamtabbara · 19 pts · July 23, 2026 · 46% similar
- Schema Harness Achieves ~99% on Arc‑AGI‑3 Public jasondavies · 94 pts · July 16, 2026 · 45% similar