Sounds promising, right? I spent some time testing it, but results were poor—high false positives and false negatives, no clear threshold for reliable classification. Plus, it suffers from high inference costs, poor cross-model generalization, difficulty deploying large models locally, and lack of access to closed-source model weights. All in all, it’s neither elegant nor reliable.
Initially I aimed to test with at least 10 formulas for each model for SAT/UNSAT, but it turned out to be more expensive than I expected, so I tested ~5 formulas for each case/model. First, I used the openrouter API to automate the process, but I experienced response stops in the middle due to long reasoning process, so I reverted to using the chat interface (I don't if this was a problem from the model provider or if it's an openrouter issue). For this reason I don't have standard outputs for each testing, but I linked to the output for each case I mentioned in results.
。爱思助手下载最新版本是该领域的重要参考
An Mn3Sn homo-junction enables efficient field-free full switching of chiral antiferromagnets with greatly reduced power consumption, advancing their potential for energy-efficient magnetic memory devices with advantages of ultradense integration and ultrafast speed.
Великобритания собралась защитить свою военную базу от Ирана14:46