Every AI leaderboard

Leaderboards28Models ranked992

28 leaderboards · 992 models ranked

ARC-AGI-2 what it measures, how it is scored and who leads it

Reasoning · ARC Prize Foundation · introduced Mar 24, 2025 · Tasks solved

Leaderboard Paper

Scores from ARC-AGI-2, published Nov 10, 2026

RankModelTasks solved
1GPT-6 AstraOpenAI · as “GPT-6 Astra (Max)”95.0%
2Gemini 4 CarbonGoogle · as “Gemini 4 Carbon (Medium)”94.2%
2GPT-6.1 SolOpenAI · as “GPT-6.1 Sol (Max)”94.2%
4Claude Fable 5.2Anthropic · as “Claude Fable 5.2 (XHigh)”93.8%
5Claude Opus 5.5Anthropic · as “Claude Opus 5.5 (High)”93.3%
6GPT-5.6 SolOpenAI · as “GPT-5.6 Sol (Max)”92.5%
7Gemini 4 ArgonGoogle · as “Gemini 4 Argon (High)”91.3%
8Claude Opus 5Anthropic · as “Claude Opus 5 (Max)”90.4%
9Claude Fable 5.1Anthropic · as “Claude Fable 5.1 (Max)”90.0%
10GPT-6 SolOpenAI · as “GPT-6 Sol (Max)”89.6%
11Claude Fable 5Anthropic · as “Claude Fable 5 (Max)”89.2%
11Gemini 3.8 FlashGoogle · as “Gemini 3.8 Flash (High)”89.2%
13GPT-5.5OpenAI · as “GPT-5.5 (XHigh)”85.0%
14Gemini 3.7 FlashGoogle · as “Gemini 3.7 Flash (High)”84.6%
15Gemini 3Google · as “Gemini 3 Deep Think (2/26)”84.6%
15GPT-5.5 ProOpenAI · as “GPT-5.5 Pro (High)”84.6%
17GPT-5.6 TerraOpenAI · as “GPT-5.6 Terra (Max)”83.9%
18Claude Sonnet 5.5Anthropic · as “Claude Sonnet 5.5 (XHigh)”83.9%
19GPT-5.4 ProOpenAI · as “GPT-5.4 Pro (XHigh)”83.3%
20Inkling 2 SmallThinking Machines · as “Inkling 2 Small (XHigh)”81.7%
21DeepSeek V4.1 FlashDeepSeek · as “DeepSeek V4.1 Flash 1017 (Max)”78.1%
22Gemini 3.1 Pro PreviewGoogle · as “Gemini 3.1 Pro (Preview)”77.1%
23Dots3 NoteDots Studio · as “Dots3-Note Preview (Max)”76.8%
24Claude 4.7Anthropic · as “Claude 4.7 (Max)”75.8%
25GPT-5.4OpenAI · as “GPT-5.4 (XHigh)”74.0%

About this benchmark

Task
Solve harder abstract grid puzzles that are easy for people and hard for AI.
Dataset
1,000 public training tasks; public, semi-private and private evaluation sets of 120 tasks each, every task solved by at least two people.
Method
Two attempts per task (pass@2), cost per task reported next to the score.
Metric
Tasks solved
Organization
ARC Prize Foundation
Introduced
Mar 24, 2025
Paper
ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems (arXiv 2505.11831)
Official leaderboard
arcprize.org/leaderboard
Home
arcprize.org/arc-agi/2/

Versions

Newest first. New versions are added, never rewritten.

VersionDate
Technical reportPaper with the human testing baseline.May 17, 20251 year ago
2Announced with ARC Prize 2025.Mar 24, 20251 year ago

Sources: each benchmark's paper (arXiv) and its official site or leaderboard. Scores are the boards captured here every day, exactly as published.