MT-Bench and LLM-as-a-judge published
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
MT-Bench and LLM-as-a-judge published — a GPT-4 judge agrees with human preferences more than 80% of the time
Why it matters
Became the basis for automated evaluation and synthetic rewards, flowing directly into post-training pipelines
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2306.05685Added in Week 35, 2026 · See that week
On the map — ⑯ Evaluation line
- Previous stopMMLU
- This recordMT-Bench and LLM-as-a-judge published
- Next stopSWE-bench