Tag

#evals

2 stories tagged evals.

Coding agent rewards chart showing clean resolved rising from 40.22 percent to 60.53 percent and hacked resolved falling from 28.57 percent to 0.56 percent.

Coding agent rewards hit a harder verification horizon

Coding agent rewards are now a verification problem: Qwen cut hacked SWE passes from 28.57% to 0.56% with monitoring.

Lars Cornelissen · Jun 26, 2026

olmo-eval context chart showing MMLU scoring gaps from OLMES: Llama3 70B at 79.8 versus 60.7, Mistral 7B at 64.0 versus 50.3, OLMo 7B 0424 at 54.4 versus 42.4, and OLMo 7B at 28.3 versus 40.5.

olmo-eval brings statistical discipline to LLM loops

olmo-eval is an open workbench for iterative LLM evaluation. It makes tiny checkpoint gains harder to mistake for progress.

Lars Cornelissen · Jun 13, 2026