AI BenchmarksTencent Releases CL-bench, a Benchmark That Exposes Context Learning Gaps in LLMs
Even GPT-5.1 solves under a quarter of tasks requiring in-context knowledge application.
Oliver SentiFeb 4, 20263 min
1 article tagged with "Fudan University"
AI BenchmarksEven GPT-5.1 solves under a quarter of tasks requiring in-context knowledge application.
Get the latest AI news, reviews, and deals delivered straight to your inbox. Join 100,000+ AI enthusiasts.
By subscribing, you agree to our Privacy Policy. Unsubscribe anytime.