Verdict
Llama 3.1-405B leads 10–2 across 12 shared benchmarks.
Llama 3.1-405B 10 · Qwen2.5-72B 2 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Commonsense Reasoning: Llama 3.1-405B leads 3–0 across 3 shared commonsense reasoning benchmarks (largest gap: Winogrande, 78.4 vs 64.6 — single evaluator).
Reasoning: Llama 3.1-405B leads 3–0 across 3 shared reasoning benchmarks (largest gap: BBH, 77.2 vs 73.07 — single evaluator).
Knowledge: Evenly split 1–1 across 2 shared knowledge benchmarks (largest gap: TriviaQA, 82.7 vs 71.9 — single evaluator).
Math: Evenly split 1–1 across 2 shared math benchmarks (largest gap: MATH level 5, 63.17 vs 49.77 — single evaluator).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Context Handling
“These are multilingual and have a significantly longer context length of 128K, state-of-the-art tool use, and overall stronger reasoning capabilities.”
General
“Llama 3.1 405B is in a class of its own, with unmatched flexibility, control, and state-of-the-art capabilities that rival the best closed source models.”
“Llama 3.1 405B is the first openly available model that rivals the top AI models when it comes to state-of-the-art capabilities in general knowledge, steerability, math, tool use”
No vendor claims on file for Qwen2.5-72B.
Llama 3.1-405B leads 10–2 across 12 shared benchmarks. Llama 3.1-405B leads 10 benchmarks and Qwen2.5-72B leads 2. Higher isn't always better — see the integrity caveats on each benchmark.
Llama 3.1-405B and Qwen2.5-72B have 12 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Llama 3.1-405B leads commonsense reasoning 3–0. Llama 3.1-405B leads reasoning 3–0.