Model Releases
Epoch continues to do some of the best public benchmarking work on AI. This is helpful (and tells us how bad the state of benchmarking is, a…
Epoch continues to do some of the best public benchmarking work on AI. This is helpful (and tells us how bad the state of benchmarking is, and how terrible some of our favorite benchmarks are) Introdu
Epoch continues to do some of the best public benchmarking work on AI. This is helpful (and tells us how bad the state of benchmarking is, and how terrible some of our favorite benchmarks are) Introducing Benchmark Reviews: our new initiative to audit AI benchmarks. We are launching with 15 benchmarks: 4 Verified, 9 Flawed, and 2 with not enough information for a review.
Related
- I find that open weights models over-perform on benchmarks compared to actual real-world usage, and Kimi feels like no exception. For exampl…
- LLMs are still not consistent judges of qualitative work, and small changes to how that work is presented affect outcomes. Better harnessing…
Source: Ethan Mollick (X) | 2026-09-18