| GPT-6 Astra: A new generation of intelligence | ✓ Link | 95.0 | GPT-6 Astra | 2026-09-03 |
| ARC Prize Leaderboard | | 94.1667 | GPT-6.1 Sol (Max) | 2026-09-29 |
| ARC Prize Leaderboard | ✓ Link | 93.3333 | Claude Opus 5.5 (High) | 2026-09-22 |
| ARC Prize Leaderboard | ✓ Link | 92.5 | GPT-5.6 Sol (Max) | 2026-07-09 |
| ARC Prize Leaderboard | ✓ Link | 91.25 | Gemini 4 Argon (High) | 2026-09-30 |
| Introducing Claude Opus 5 | ✓ Link | 90.42 | Claude Opus 5 | 2026-07-24 |
| ARC Prize Leaderboard | | 90.0 | Claude Fable 5.1 (Max) | 2026-09-01 |
| ARC Prize Leaderboard | | 89.5833 | GPT-6 Sol (Max) | 2026-09-22 |
| ARC Prize Leaderboard | ✓ Link | 89.167 | Claude Fable 5 (Max) | 2026-06-09 |
| ARC Prize Leaderboard | ✓ Link | 89.1667 | Gemini 3.8 Flash (High) | 2026-09-02 |
| Introducing GPT-5.5 | | 85.0 | GPT-5.5 | 2026-04-23 |
| ARC Prize Leaderboard | | 84.58 | Gemini 3 Deep Think (2/26) | 2025-11-18 |
| ARC Prize Leaderboard | | 83.33 | GPT-5.4 Pro (XHigh) | 2026-03-05 |
| Gemini 3.1 Pro: A smarter model for your most complex tasks | | 77.1 | Gemini 3.1 Pro | 2026-02-19 |
| ARC Prize Leaderboard | | 75.83 | Claude 4.7 (Max) | 2026-04-16 |
| ARC Prize Leaderboard | ✓ Link | 72.9167 | DeepSeek V4.1 Flash (Max) | 2026-09-17 |
| ARC Prize Leaderboard | | 72.08 | Gemini 3.5 Flash (High) | 2026-05-19 |
| ARC Prize Leaderboard | | 72.08 | Claude Opus 4.8 (High) | 2026-05-28 |
| ARC Prize Leaderboard | | 69.17 | Claude Opus 4.6 (120K, High) | 2026-02-05 |
| ARC Prize Leaderboard | | 67.0833 | Grok 4.6 (XHigh) | 2026-08-12 |
| ARC Prize Leaderboard | ✓ Link | 65.8333 | GLM-5.3-Flash (Max) | 2026-08-26 |
| ARC Prize Leaderboard | ✓ Link | 61.389 | DeepSeek V4 Flash 0731 (Max) | 2026-04-26 |
| ARC Prize Leaderboard | | 61.2500 | Claude Haiku 5.5 (XHigh) | 2026-10-07 |
| ARC Prize Leaderboard | | 60.42 | Claude Sonnet 4.6 (High) | 2026-02-17 |
| ARC Prize Leaderboard | | 60.417 | Gemini 3.6 Flash (High) | 2026-07-21 |
| ARC Prize Leaderboard | ✓ Link | 60.417 | Kimi K3 (Max) | 2026-07-27 |
| Introducing GPT-5.2 | | 54.2 | GPT-5.2 Pro | 2025-12-11 |
| ARC Prize Leaderboard | | 52.64 | Grok 4.5 (High) | 2026-07-08 |
| The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows | ✓ Link | 50.0 | ReASearch | 2026-08-07 |
| Inkling-Small | ✓ Link | 40.1 | Inkling-Small | 2026-07-27 |
| ARC Prize Leaderboard | ✓ Link | 36.528 | Inkling | 2026-07-15 |
| Introducing Gemini 3 Flash | | 33.6 | Google Gemini 3 Flash (Thinking) | 2025-12-17 |
| ARC Prize Leaderboard | | 27.64 | NVARC | 2026-01-15 |
| ARC Prize Leaderboard | ✓ Link | 22.7750 | GLM-5.2 | 2026-06-16 |
| Natural Image Pretraining Improves Abstract Reasoning | | 13.1 | Nat-ARC ensemble | 2026-09-08 |
| ARC Prize Leaderboard | ✓ Link | 11.81 | Kimi K2.5 | 2026-02-02 |
| ARC Is a Vision Problem! | | 11.1 | VARC (ensemble) | 2025-11-18 |
| ARC Is a Vision Problem! | | 8.3 | VARC | 2025-11-18 |
| ARC Prize Leaderboard | ✓ Link | 6.53 | o3 (High) | 2025-04-16 |
| ARC Prize Leaderboard | ✓ Link | 6.25 | Tiny Recursion Model (TRM) | 2025-10-06 |
| Hierarchical Reasoning Model | ✓ Link | 5.0 | HRM | 2025-06-26 |
| ARC Prize Leaderboard | | 4.86 | Gemini 2.5 Pro (Thinking 32K) | 2025-07-07 |
| ARC Prize Leaderboard | ✓ Link | 4.86 | MiniMax M2.5 | 2026-02-12 |
| ARC Prize Leaderboard | ✓ Link | 4.03 | Deepseek V3.2 | 2025-12-02 |
| ARC Prize Leaderboard | | 2.5 | ARChitects | 2024-12-05 |
| ARC Prize Leaderboard | | 0.9 | Claude 3.7 (8K) | 2025-02-24 |
| ARC Prize Leaderboard | ✓ Link | 0.0 | Llama 4 Maverick | 2025-04-05 |
| ARC Prize Leaderboard | | 0.0 | Magistral Medium (Thinking) | 2025-06-12 |