BenchLeader

LLaMA-65B

LLaMA-65B is a Meta open-weights model, released 24 Feb 2023. It is not yet ranked: 1 independent result so far, and the index needs at least five across two categories. Last measured 24 Feb 2023.stale: no new result in six months

Blended price
–
Output speed
–
First answer
–
Context
2k
Full answer
–
Cost per run
–
Released
24 Feb 2023
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Composite35

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
HellaSwagnot in index84.2%#12Epoch AI Benchmarking Hub
BIG-Bench Hardnot in index58.4%#17Epoch AI Benchmarking Hub
WinoGrandenot in index77.0%#26Epoch AI Benchmarking Hub
ARC (AI2 Challenge)not in index69.5%#24Epoch AI Benchmarking Hub
PIQAnot in index82.8%#16Epoch AI Benchmarking Hub

Maths

Benchmarknot statedSourceTrend
GSM8Knot in index54.4%#32Epoch AI Benchmarking Hub

Knowledge

Benchmarknot statedSourceTrend
MMLUnot in index63.4%#73Epoch AI Benchmarking Hub
TriviaQAnot in index86.0%#5Epoch AI Benchmarking Hub
OpenBookQAnot in index60.2%#13Epoch AI Benchmarking Hub
LAMBADAnot in index77.7%#7Epoch AI Benchmarking Hub

Composite

More from Meta

New this month

See also

Questions people ask

Why does LLaMA-65B have no BenchLeader Index score?
The index needs at least five independent results across at least two categories; as of 25 Oct 2026 LLaMA-65B has 1 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
When was LLaMA-65B released?
Meta released LLaMA-65B on 24 Feb 2023.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “LLaMA-65B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/llama-65b.