ARC-AGI-2
Updated May 2, 2026·4,883 views
- Problem Count
- 1000
- Institution
- —
- Category
- General Evaluation
- Metrics
- Accuracy
- Language
- English
- Difficulty
- Mixed
Overview
ARC-AGI-2 is an AI benchmark used to evaluate model capabilities. Review its overview, metrics, official resources, and model leaderboard results on DataLearnerAI.
Related resources
Latest ARC-AGI-2 model rankings and full benchmark leaderboard
Browse the latest scores, model modes, release dates, and parameter sizes for ARC-AGI-2.
Source: DataLearnerAI
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model Mode Legend
License:
Origin:
Model release cutoff:
1 parallel-mode results hidden
ARC-AGI-2 Rank
| Rank | Model | License | |||
|---|---|---|---|---|---|
 GPT-5.5 Thinking Level · Extra High | 85.00 | 2026-04-23 | Unknown | Closed | |
 Gemini 3 Deep Think - 2620 Thinking Enabled | 84.60 | 2026-02-13 | Unknown | Closed | |
GPT-5.5 Pro Thinking Level · High | 84.60 | 2026-04-23 | Unknown | Closed | |
4 | GPT-5.5 Pro Thinking Level · Extra High | 84.20 | 2026-04-23 | Unknown | Closed |
5 | GPT-5.4 Pro Thinking Level · High | 83.30 | 2026-03-05 | Unknown | Closed |
6 | GPT-5.5 Thinking Level · High | 83.30 | 2026-04-23 | Unknown | Closed |
7 | Gemini 3.1 Pro Preview Thinking Level · High | 77.10 | 2026-02-20 | Unknown | Closed |
8 | GPT-5.4 Standard Mode | 77.10 | 2026-03-05 | Unknown | Closed |
9 |  Opus 4.7 Thinking Level · High | 75.80 | 2026-04-16 | Unknown | Closed |
10 | GPT-5.4 Thinking Level · Extra High | 74.00 | 2026-03-05 | Unknown | Closed |
11 | GPT-5.5 Thinking Level · Medium | 70.40 | 2026-04-23 | Unknown | Closed |
12 | Opus 4.7 Thinking Level · High | 68.30 | 2026-04-16 | Unknown | Closed |
13 | Opus 4.7 Thinking Level · Medium | 67.50 | 2026-04-16 | Unknown | Closed |
14 | Claude Opus 4.6 Extended Thinking | 66.30 | 2026-02-05 | Unknown | Closed |
15 | Claude Opus 4.6 Thinking Level · Low | 64.60 | 2026-02-05 | Unknown | Closed |
16 | Opus 4.7 Thinking Level · Low | 62.10 | 2026-04-16 | Unknown | Closed |
17 | Claude Sonnet 4.6 Thinking Enabled | 58.30 | 2026-02-17 | Unknown | Closed |
18 | GPT-5.4 Thinking Level · Medium | 55.40 | 2026-03-05 | Unknown | Closed |
19 | GPT-5.2 Parallel · Deep Thinking Mode | 54.20 | 2025-12-11 | Unknown | Closed |
20 | GPT-5.2 Pro Thinking Enabled | 54.20 | 2025-12-11 | Unknown | Closed |
21 | GPT-5.2 Thinking Level · Extra High | 52.90 | 2025-12-11 | Unknown | Closed |
22 | GPT-5.2 Thinking Level · High | 43.30 | 2025-12-11 | Unknown | Closed |
23 |  Muse Spark Thinking Enabled | 42.50 | 2026-04-08 | Unknown | Closed |
24 | Opus 4.5 Extended Thinking | 37.60 | 2025-11-25 | Unknown | Closed |
25 | Gemini 3.0 Flash Thinking Enabled | 33.60 | 2025-12-17 | Unknown | Closed |
26 | GPT-5.5 Thinking Level · Low | 33.30 | 2026-04-23 | Unknown | Closed |
27 | Gemini 3.0 Pro (Preview 11-2025) Thinking Enabled | 31.10 | 2025-11-18 | Unknown | Closed |
28 | GPT-5.4 Thinking Level · Low | 29.20 | 2026-03-05 | Unknown | Closed |
29 | GPT-5.2 Thinking Level · Medium | 26.70 | 2025-12-11 | Unknown | Closed |
Scroll to load 28 more