Llama-3.1-70B-Instruct
Llama-3.1-70B-Instruct is developed by Meta, released 2024-07-23.
Also written as: Llama 3.1 70B Instruct
Model ID: llama-3.1-70b-instruct
Input price
—
Output price
—
Blended price
—
Epoch Capabilities Index (ECI)
No public data yet
Epoch Mock AIME accuracy
3.6%
Epoch AI · as of 2024-07-23
Epoch FrontierMath (T1–3) accuracy
No public data yet
Arena text rating
1293.4
10th percentile of 164 models with an Arena text rating score
LMArena · as of 2026-11-06
Arena coding rating (human preference votes, not task accuracy)
1333.0
LMArena · as of 2026-11-06
Arena math rating
1269.1
LMArena · as of 2026-11-06
Arena WebDev rating
No public data yet
No API price is published for this model in our data sources (models.dev,
LiteLLM), so we show — rather than guess. It may be unreleased via API, open-weights
only, or simply not tracked yet.
See all of Meta's models on its provider page, or browse the full model directory. Full source licenses and sync dates: /data-sources/.