Verdict
Evenly split 4–4 across 8 shared benchmarks.
Claude 3 Opus 4 · Llama 3.1-405B 4 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Math: Llama 3.1-405B leads 2–0 across 2 shared math benchmarks (largest gap: MATH level 5, 49.77 vs 37.48 — single evaluator).
Reasoning: Evenly split 1–1 across 2 shared reasoning benchmarks (largest gap: GPQA diamond, 34.55 vs 29.55 — 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.
No vendor claims on file for Claude 3 Opus.
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”
Evenly split 4–4 across 8 shared benchmarks. Claude 3 Opus leads 4 benchmarks and Llama 3.1-405B leads 4. Higher isn't always better — see the integrity caveats on each benchmark.
Claude 3 Opus and Llama 3.1-405B have 8 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 math 2–0.