Llama 2 Chat 13B — benchmark results

Provider: Meta. Released 2023-07-18. Access: Open.

Unified ELO 1282 ± 72, rank #1630 of 1841 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Humanity's Last Exam4.73Accuracy (%)26.9
Epoch AI - Scicode11.81Score11.3
AA GPQA Diamond32.12Accuracy (%)9.6
AA MMLU-Pro40.63Accuracy (%)8.1
AA MATH-50032.87Accuracy (%)7.8
AA LiveCodeBench9.84Pass@1 (%)7.7
Artificial Analysis Intelligence Index3Intelligence Index7.5

Interactive version: theaggregate.ai/model?slug=llama-2-chat-13b · How It Works · Data refreshed daily, snapshot 2026-07-25.