SLM Leaderboard

Small Language Model Performance & Efficiency Index

Total Evaluated SLMs
0
Active Community Leaderboard
Top Intelligence Score
0.0%
-
Evaluation Suite
5 Benchmarks
Standard evaluation
Parameter Cap
< 500 Million
Focused strictly on sub-500M edge & small AI

Benchmark Leaderboard

Sort by weighted overall score or individual benchmark metrics.

Rank Model Creator / Org Params Overall Index AIME 2026 (1.5x) ARC-E (1.0x) ARC-C (0.5x) PIQA (1.0x) HellaSwag (1.0x) Card

Intelligence Index vs. Parameter Count

Logarithmic scale X-axis with average trend vs Top-10% efficiency frontier.

Creator / Org Share

Distribution of submitted SLMs by organization or individual creator.

Per-Model Radar & Skill Insights

Analyze benchmark strengths/weaknesses compared against the overall SLM average.

Benchmark Strengths

Optimization Opportunities