I also tested it[0]: quite similar to GLM 5, a few percent better, 30% faster and 50% more expensive.
[0]: https://aibenchy.com/?q=glm
PS: Just added a cool feature, so you can filter the leaderboard for multiple models at once, by using a comma, like: https://aibenchy.com/?q=glm,claude
benchmark where gemini flash is better than fable btw.
still 1/4 of the price of anthropic and openai models though
PS: Just added a cool feature, so you can filter the leaderboard for multiple models at once, by using a comma, like: https://aibenchy.com/?q=glm,claude