Llama 3.1 405B vs Llama 3.1 70B
Change modelsLlama 3.1 405BMeta
Llama 3.1 70BMeta
IndexAll categories, out of 100.
27.0 ±8.9 best
24.8 ±5.3
GapIndex points below the top.
Top
−2.2 · no clear gap
CoverageIndex weight that has results.
65%
90% best
SpeedOutput tokens per second.
29/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2024-07
2024-07
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
128K
128K
AgenticMulti-step tasks with tools.
15.4
17.1 best
CodingCode writing and repair.
—
21.4
ReasoningLogic problems and puzzles.
30.8 best
23.7
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
26.3
27.6 best
MultilingualTasks in many languages.
—
41.0
InstructionTasks with strict prompt rules.
33.5 best
27.8
MathMath problems.
18.9 best
13.9
Benchmarks
10 sharedOnly Llama 3.1 70B: 10
Llama 3.1 405B
Llama 3.1 70B