🛠️ Redactle LLM Leaderboard
Summary
A leaderboard evaluating how well different language models play Redactle. It reveals that Gemini Flash outperforms others significantly in both performance and cost.
Why it’s interesting
It demonstrates that Gemini Flash can one-shot every evaluation in a few seconds, outperforming other models in the Redactle game.
Source metrics: Points 4 · Comments 1
HN discussion · Project
Source: #HackerNews / Show HN
Summary
A leaderboard evaluating how well different language models play Redactle. It reveals that Gemini Flash outperforms others significantly in both performance and cost.
Why it’s interesting
It demonstrates that Gemini Flash can one-shot every evaluation in a few seconds, outperforming other models in the Redactle game.
Source metrics: Points 4 · Comments 1
HN discussion · Project
Source: #HackerNews / Show HN