WhirlwindAI/MetaNova-0.1-70M

⚡ At a Glance

🟣 Quick summary — The WhirlwindAI MetaNova models each have their own strengths: MetaNova-0.1-70M leads on ArithMark-2, while MetaNova-Test takes ARC-Challenge. Supra-50M-Base (external baseline) posts the highest Final Avg at 38.60% with the smallest parameter count.

🏁 Full Leaderboard

_{🏆 = best score in the row. Bold = row winner.}

📊 Metric-by-Metric View

🧠 THINKING Chat Format

<|im_start|>user
{query} /think<|im_end|>
<|im_start|>assistant
<think>
{thinking_content}
</think>
{response}<|im_end|>

<|im_start|>user
{query} /no_think<|im_end|>
<|im_start|>assistant
<think>

</think>

{response}<|im_end|>

  </td>
</tr>

🔵 blue = user / assistant content  •  🔴 red = mode switch + reasoning block

🧾 Run Summary

_{⭐ If this model helped you, consider leaving a like on the Hub.}

_{WhirlwindAI · 2026}