🔥 Trending today
First GPT-5.6 tests arrive, targeting Mythos
量子位 QbitAI4 days agoBenchmarkThe title indicates that QbitAI is covering the first hands-on tests of GPT-5.6, framed around a comparison with Mythos. Because the article body is unavailable, the testing setup, metrics, task types, and actual performance gap cannot be verified. The item is best treated as an early benchmark or model-comparison report that needs the original article for proper evaluation.
Reality: The Final Eval — Lukas Petersson and Axel Backlund of Andon Labs
Latent Space10 days agoBenchmarkLatent Space talks with Lukas Petersson and Axel Backlund of Andon Labs, the authors behind VendingBench. The episode focuses on evaluating Claude models across a range from Haiku to Mythos. It also discusses how they build frontier evals from scratch, with an emphasis on creating benchmarks that remain useful and meaningful over time.