ARC Prize

@arcprize

A North Star for open AGI. Co-founders: @fchollet @mikeknoop. President: @gregkamradt. We're hiring mission-driven builders: arcprize.org/jobs

Earth

Joined March 2024

Pinned
ARC Prize
@arcprize
Mar 25
Announcing ARC-AGI-3 The only unsaturated agentic intelligence benchmark in the world Humans score 100%, AI <1% This human-AI gap demonstrates we do not yet have AGI Most benchmarks test what models already know, ARC-AGI-3 tests how they learn
GIF
ARC Prize
@arcprize
Aug 14
Grok 4.6 from @SpaceXAI on ARC-AGI (Verified): - ARC-AGI-1: 87.5%, $0.30/task - ARC-AGI-2: 67.1%, $0.76/task - ARC-AGI-3: 2.11%, $5.6K On ARC-AGI-3, Grok 4.6 with xhigh reasoning scored comparably to GPT-5.6 Sol with high reasoning, but cost $5.6K versus Sol's $15.2K.
ARC Prize
@arcprize
Aug 7
DeepSeek V4 Flash from @deepseek_ai on ARC-AGI (Verified): - ARC-AGI-2: 61.4%, $0.04/task - ARC-AGI-1: 89.0%, $0.02/task DeepSeek V4 Flash sets the new standard on the cost-to-performance Pareto frontier.
ARC Prize
@arcprize
Aug 6
Gemini 3.6 Flash and 3.5 Flash-Lite from @Google on ARC-AGI (Verified): 3.6 Flash: - ARC-AGI-2: 60.4%, $0.61/task - ARC-AGI-1: 91.2%, $0.34/task 3.5 Flash-Lite: - ARC-AGI-2: 10.3%, $0.14/task - ARC-AGI-1: 53.5%, $0.09/task
ARC Prize
@arcprize
Aug 6
We re-tested GPT-5.6 Luna from @OpenAI on ARC-AGI (Verified) following its recent 80% price reduction: - ARC-AGI-2: 59.6%, $0.18/task - ARC-AGI-1: 90.7%, $0.07/task The new results match Luna's original performance at a much lower cost.