Llama 7B Agentic

NEW HOT

Meta AI · Llama

Open Source

An advanced small-scale Llama model optimized for multi-step agentic workflows and complex reasoning tasks.

TextReasoningAgents

Scores 68% on MMLU, competitive across 4 standard benchmarks.

Data aggregated and editorially reviewed by TrendMing.

Benchmark Performance

MMLU68%
HumanEval55%
MATH32%
GPQA28%

Scores sourced from published evaluations. Higher = better.

Quick Specs

Context Window64K tokens
Parameters7B
Input pricingN/A (self-hosted)
Output pricingN/A (self-hosted)
Released2026-03-15