ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export
mhmazur · x · 2026-10-27
ARC Prize's mhmazur is soliciting feedback on a leaderboard redesign: it now shows each model's highest reasoning level by default (with a toggle for all levels), sortable v1/2/3 scores to quickly find top performers per benchmark, search/filter across model, provider, effort, benchmark and result details, CSV download or clipboard copy for custom analysis, remembered settings, and improved responsive behavior. Easier raw public v1/2/3 test data downloads ship later. Screenshot: Gemini 4 Argon leads with 98.5% on ARC-AGI-1 ($0.162/task) and 91.3% on ARC-AGI-2; DeepSeek V4.1 Flash 1017 posts 94.5%/78.1%.
More from Models
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27
- Fable 5.5 rumored to ship this week as partners still test — kimmonismus · 2026-10-27
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27