Grok 2 vs Llama 3.3 70B
Change modelsGrok 2xAI
Llama 3.3 70BMeta
IndexAll categories, out of 100.
29.1 ±9.4 best
28.2 ±5.3
GapIndex points below the top.
Top
−0.9 · no clear gap
CoverageIndex weight that has results.
55%
90% best
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
1305
—
ReleasedMonth of release.
2024-08
2024-12
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
AgenticMulti-step tasks with tools.
—
27.2
CodingCode writing and repair.
25.2
28.9 best
ReasoningLogic problems and puzzles.
—
27.5
MultimodalTasks with images and text.
33.5
—
KnowledgeFacts and expert knowledge.
34.0 best
29.1
MultilingualTasks in many languages.
—
34.1
InstructionTasks with strict prompt rules.
—
40.9
MathMath problems.
25.0 best
15.6
Benchmarks
7 sharedOnly Grok 2: 12Only Llama 3.3 70B: 9
Grok 2
Llama 3.3 70B