Llama 2-70B vs PaLM 2-L

Verdict

Evenly split 2–2 across 4 shared benchmarks.

Llama 2-70B 2 · PaLM 2-L 2 · higher isn't always better — see caveats.

Per-benchmark head-to-head

Llama 2-70BPaLM 2-L

71.07
ARC AI2
58.93
80.4
HellaSwag
82.4
87.6
TriviaQA
86.1
60.4
Winogrande
66

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
PaLM 2-L86.1