RankingARC-AGI-2
ARC-AGI-2
- Bucket
- Hard reasoning
- Unit
- percent
- Direction
- Higher is better
- Version
- 2
- Display harness
- ARC Prize verified
- Board
- https://arcprize.org/leaderboard
Compare published benchmark results with category weights →
Models
51–75 of 471 entries
| Model | Score | Evidence | Source-recorded date |
|---|---|---|---|
| GPT-5 NanoOpenAI | 2.6% | official board | 2025-08-07 |
| Gemini 2.5 FlashGoogle | 1.7% | official board | 2025-05-20 |
| Claude Haiku 4.5Anthropic | 1.3% | official board | 2025-10-01 |
| Qwen3-235B-A22B-Instruct-2507Qwen | 1.3% | official board | 2025-07-25 |
| GPT-4.1OpenAI | 0.4% | official board | 2025-04-14 |
| GPT-4.1 MiniOpenAI | 0% | official board | 2025-04-14 |
| GPT-4.1-nanoOpenAI | 0% | official board | 2025-04-14 |
| GPT-4oOpenAI | 0% | official board | 2024-11-20 |
| GPT-4o MiniOpenAI | 0% | official board | 2024-07-18 |
| Llama 4 MaverickMeta | 0% | official board | 2025-04-05 |
| Agnes 2.5 Pro AlphaAgnes AI | — | — | — |
| Agnes-3.0-Flash PreviewAgnes AI | — | — | — |
| Amazon Nova 2 LiteAmazon | — | — | — |
| Amazon Nova 2 Pro PreviewAmazon | — | — | — |
| Amazon Nova LiteAmazon | — | — | — |
| Amazon Nova MicroAmazon | — | — | — |
| Amazon Nova PremierAmazon | — | — | — |
| Amazon Nova ProAmazon | — | — | — |
| AutoGLM-Phone-9BZ.ai | — | — | — |
| AutoGLM-Phone-9B-MultilingualZ.ai | — | — | — |
| aya-101Cohere | — | — | — |
| aya-23-35BCohere | — | — | — |
| aya-23-8BCohere | — | — | — |
| aya-expanse-8bCohere | — | — | — |
| aya-vision-8bCohere | — | — | — |