AlpacaEval vs ARC-AGI-1
Select two to four listings to compare their details.
Scroll sideways to see all listings.
| Name | AlpacaEval | ARC-AGI-1 |
|---|---|---|
| City and region | Online, Global | Online, Global |
| Categories | Reasoning | Reasoning |
| Phone | — | — |
| Website | https://github.com/tatsu-lab/alpaca_eval | https://github.com/fchollet/ARC-AGI |
| Tier | free | free |
| Tags | Helpful, Science | Viral, Science |
| Category | Reasoning | Reasoning |
| Status | Active | Active |
| Saturation | — | — |
| Data licence | Apache-2.0 | Apache-2.0 |
| Data access | open | open |
| Grader | llm-judge | exact |
| Organization | Stanford CRFM | François Chollet |
| Released | 2023-05 | 2019-11 |
| Paper | https://arxiv.org/abs/2404.04475 | https://arxiv.org/abs/1911.01547 |
| Leaderboard | https://tatsu-lab.github.io/alpaca_eval/ | https://arcprize.org/leaderboard |
| Repository | https://github.com/tatsu-lab/alpaca_eval | https://github.com/fchollet/ARC-AGI |
| npm package | — | — |
| Task count | 805 | 800 |
| Top-score provenance | unknown | unknown |
| Top score | — | — |
| Top-score source | — | — |
| ABI family | No | No |
Published by AI Benchmark Index. How we check each benchmark.