[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

[@arcprize](/creator/twitter/arcprize)
"New SOTA on ARC-AGI - V1: XXXX% $8.42/task - V2: XXXX% $30.40/task Custom submissions by @jerber888 and @_eric_pang_ are now the best known solutions to ARC-AGI Both: * Are open source * Use Grok X * Implement program-synthesis outer loops with test-time adaptation"  
[X Link](https://x.com/arcprize/status/1967998885701538060) [@arcprize](/creator/x/arcprize) 2025-09-16T17:07Z 28.5K followers, 7.5M engagements


"Grok-4 (Fast Reasoning) on ARC-AGI Semi Private Eval - ARC-AGI-1: XXXX% $0.03/task - ARC-AGI-2: XXX% $0.06/task @xai pushes the frontier of performance efficiency on ARC-AGI"  
[X Link](https://x.com/arcprize/status/1980675418777870574) [@arcprize](/creator/x/arcprize) 2025-10-21T16:39Z 28.5K followers, 1.6M engagements


"Grok X (Thinking) achieves new SOTA on ARC-AGI-2 with XXXX% This nearly doubles the previous commercial SOTA and tops the current Kaggle competition SOTA"  
[X Link](https://x.com/arcprize/status/1943168950763950555) [@arcprize](/creator/x/arcprize) 2025-07-10T04:42Z 28.5K followers, 7.3M engagements


"Today we're announcing a preview of ARC-AGI-3 the Interactive Reasoning Benchmark with the widest gap between easy for humans and hard for AI Were releasing: * X games (environments) * $10K agent contest * AI agents API Starting scores - Frontier AI: X% Humans: 100%"  
[X Link](https://x.com/arcprize/status/1946260363256996244) [@arcprize](/creator/x/arcprize) 2025-07-18T17:26Z 28.5K followers, 410.1K engagements


"New ARC-AGI SOTA: GPT-5 Pro - ARC-AGI-1: XXXX% $4.78/task - ARC-AGI-2: XXXX% $7.41/task @OpenAIs GPT-5 Pro now holds the highest verified frontier LLM score on ARC-AGIs Semi-Private benchmark"  
[X Link](https://x.com/arcprize/status/1976329182893441209) [@arcprize](/creator/x/arcprize) 2025-10-09T16:49Z 28.5K followers, 558.8K engagements


"Tiny Recursion Model (TRM) results on ARC-AGI - ARC-AGI-1: XX% $1.76/task - ARC-AGI-2: XXX% $2.10/task Thank you to @jm_alexia for contributing TRM a well written open source and thorough research to the community based on the HRM from @makingAGI"  
[X Link](https://x.com/arcprize/status/1978872651180577060) [@arcprize](/creator/x/arcprize) 2025-10-16T17:16Z 28.5K followers, 268.4K engagements


"NeurIPS Party - ARC Prize Foundation + Y Combinator Join us in San Diego for a NeurIPS party co-hosted with @ycombinator Meet ARC Prize and YC leadership researchers and industry leaders pushing the boundaries of frontier AI San Diego 6-8 PM December X 2025"  
[X Link](https://x.com/arcprize/status/1983939623224054112) [@arcprize](/creator/x/arcprize) 2025-10-30T16:50Z 28.5K followers, 108.1K engagements