DeepSeek R1 vs Llama 3.1 405B Instruct
As of Oct 14, 2026, DeepSeek R1 leads Llama 3.1 405B Instruct in 1 of 2 shared categories: Science.
DeepSeek R1
It used to be. Was SOTA in General LLM.
Llama 3.1 405B Instruct
It used to be. Was SOTA in General LLM.
| Category | DeepSeek R1 | Llama 3.1 405B Instruct |
|---|---|---|
| General LLM | #118 · Was SOTA · General LLM Margin 80.27210884353741 LMArena leaderboard dataset · Oct 13, 2026 | #3 · #3 in General LLM Margin — LMArena leaderboard dataset · Sep 4, 2024 |
| Reasoning | #116 · Was SOTA · Reasoning Margin 80.13698630136986 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Sep 4, 2024 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | — |
| Science | #90 · #90 in Science Margin — Epoch AI benchmarking hub · Jan 20, 2025 | #124 · #124 in Science Margin — Epoch AI benchmarking hub · Jul 23, 2024 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #123 · Was SOTA · Long context Margin 83.6734693877551 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Abstraction (ARC) | #77 · #77 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Jan 20, 2025 | — |
DeepSeek R1: $1.15 per 1M blended tokens.
Llama 3.1 405B Instruct: price per 1M tokens is unset in the catalog.
DeepSeek R1: open weights.
Llama 3.1 405B Instruct: open weights.
General LLM: As of Oct 14, 2026, Llama 3.1 405B Instruct leads DeepSeek R1 in General LLM at #3 against #118.
Science: As of Oct 14, 2026, DeepSeek R1 leads Llama 3.1 405B Instruct in Science at #90 against #124.
DeepSeek R1 · Llama 3.1 405B Instruct
DeepSeek R1 or Llama 3.1 405B Instruct?
As of Oct 14, 2026, DeepSeek R1 leads Llama 3.1 405B Instruct in 1 of 2 shared categories: Science.
DeepSeek R1 or Llama 3.1 405B Instruct for General LLM?
As of Oct 14, 2026, Llama 3.1 405B Instruct leads DeepSeek R1 in General LLM at #3 against #118.
DeepSeek R1 or Llama 3.1 405B Instruct for Science?
As of Oct 14, 2026, DeepSeek R1 leads Llama 3.1 405B Instruct in Science at #90 against #124.