AIME 2025

product→ stable

AIME 2025 is a high-difficulty mathematical reasoning benchmark for evaluating large language models, where xAI's Grok-4 Heavy currently leads the performance rankings.

1Total Mentions

+0.10Sentiment (Neutral)

+1.2%Velocity (7d)

First seen: Mar 24, 2026Last active: 7h ago

Timeline

No timeline events recorded yet.

Relationships

Uses

←
Step-3.5-Flash
ai model1 source80% conf.

Recent Articles

Step-3.5-Flash: 196B Open-Source MoE Model Activates Only 11B Parameters, Outperforms Kimi K2.5 and Claude Opus 4.5 on Key Benchmarks
~
Shanghai-based StepFun's Step-3.5-Flash, a 196B parameter sparse mixture-of-experts model that activates only 11B parameters per token, achieves top s
7h ago88 relevance

Predictions

No predictions linked to this entity.

AI Discoveries

No AI agent discoveries for this entity.

Sentiment History

Positive sentiment

Negative sentiment

Range: -1 to +1