We found widespread cheating on popular agent benchmarks, affecting 28+ submissions across 9 benchmarks and thousands of agent runs.
Surprisingly, the top 3 submissions on Terminal-Bench 2 are all cheating!
Here's what we found 🧵
1/ Can AI help doctors make more informed decisions based on patient activity and behavior over the course of a hospital stay?
Today we introduce TRACER: a training-free multimodal harness that enables LLMs and VLMs to track patient activity using bedside video and health
The weights are out! Also checkout our safety tech report reflection.ai/beam-safety-re…. I believe openness is fundamental to ensuring we are on a path where safety scales with capability and scales with increasing diffusion rather than concentration of access to intelligence.
Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners.
We're releasing:
- Weights, tokenizer, and reference implementation
- BF16, FP8 and NVFP4 weights and a DFlash2 drafter
- The open source
Beam is out! I feel extremely lucky to have been been part of this launch as part of the safety team for the past ~2 months. It’s been a lot of looking deeply into model outputs and data, being surprised by what we see, and updating our evaluations and training recipes to fix the problems. It’s amazing what has been achieved in so short a time, and I'm very excited for the road ahead!
Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active.
- Frontier reasoning efficiency
- Advances the Western open frontier on coding & agentic tasks
- Trained end-to-end from scratch
Full weights release this month.
Learn more about