ARC Prize arcprize.org ↗
A benchmark and competition that tests abstract reasoning and generalization in AI systems.
OtherAI & MLbenchmarkagiabstraction
Captured
Recommended in 1 thread
The end of Microsoft Research's AI Frontiers grouphunch.net ·
Cited as another way of framing what intelligence is.
Similar tools
- Artificial Analysis Decision Index ↗AI & ML1 thread
A benchmark comparing decision models on quality and price.
- TaxCalcBench ↗AI & ML1 thread
An open benchmark from Column Tax for evaluating AI models on tax calculations.
- Artificial Analysis ↗AI & ML7 threads
A site benchmarking and comparing AI models on quality, price and speed.
- DataAgentBench ↗AI & ML1 thread
A UC Berkeley benchmark and leaderboard for data agents that query multiple sources.
- ExLlamaV3 ↗AI & ML0 threads
A quantization and inference library for running LLMs on consumer and datacenter GPUs.
- Liquid AI Decision Models ↗AI & ML1 thread
Models from Liquid AI trained specifically to produce decisions with calibrated confidence.
- 1 thread
- 1 thread
Also in AI & ML
- 19 threads
- 12 threads
- 12 threads
- 11 threads
- 9 threads
- 8 threads
- 7 threads
- 7 threads
- 5 threads
- 5 threads
- 4 threads
- 4 threads
Link from a commenter, not checked or endorsed by us: ↗ https://arcprize.org/