LLaMA-13B: benchmark results

Provider: Meta. Released 2023-02-24. Access: Open.

Unified ELO 1335 ± 1, rank #1292 of 1392 rated models, from 122 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ToolBench - WebShop Short27.6Task Score90.7
HELM Classic - bAbI56.07Exact Match (%)84.1
HELM Classic - Entity Matching85.92Exact Match (%)80.3
MMLU-by-task - College Mathematics36Accuracy (%)80.3
HELM Classic - Dyck68.6Exact Match (%)80.1
HELM Classic - LegalSupport58.69Exact Match (%)77.9
HELM Classic - CivilComments59.98Exact Match (%)77.3
HELM Classic - NarrativeQA71.12F1 (%)75.4
HELM Classic - TruthfulQA32.42Exact Match (%)74.2
HELM Classic - GSM8K15.4Exact Match (%)73.5
HELM Classic - MATH Chain-of-Thought10.98Equivalent (%)73.5
HELM Classic - Entity Data Imputation82.42Exact Match (%)72.7

Interactive version: theaggregate.ai/model?slug=llama-13b · How It Works · Data refreshed daily, snapshot 2026-09-05.