Llama 2-70B vs LLaMA-65B

Verdict

Llama 2-70B leads 8–0 across 10 shared benchmarks.

Llama 2-70B 8 · LLaMA-65B 0 · 2 tied · higher isn't always better — see caveats.

Per-benchmark head-to-head

Llama 2-70BLLaMA-65B

71.07
ARC AI2
59.33
53.2
BBH
44.53
69.6
GSM8K
54.4
80.4
HellaSwag
78.93
78.9
LAMBADA
77.7
59.87
MMLU
51.2
46.93
OpenBookQA
46.93
65.6
PIQA
65.6
87.6
TriviaQA
86
60.4
Winogrande
54

A higher number is not always a better model. Each score is task performance under a disclosed harness, and some of these benchmarks are saturated or scored under mixed harnesses. Follow any benchmark to its integrity grade before reading a win as decisive.

Follow the record

These models

Llama 2-70B87.6
LLaMA-65B86