Llama 3.1 70B vs Mistral Small 3.1
Change modelsLlama 3.1 70BMeta
Mistral Small 3.1Mistral
IndexAll categories, out of 100.
24.8 ±5.3 best
24.2 ±4.1
GapIndex points below the top.
Top
−0.6 · no clear gap
CoverageIndex weight that has results.
90%
95% best
SpeedOutput tokens per second.
—
28/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2024-07
2025-03
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.
17.1
26.7 best
CodingCode writing and repair.
21.4
25.6 best
ReasoningLogic problems and puzzles.
23.7
29.7 best
MultimodalTasks with images and text.
—
28.8
KnowledgeFacts and expert knowledge.
27.6 best
25.7
MultilingualTasks in many languages.
41.0
—
InstructionTasks with strict prompt rules.
27.8 best
17.0
MathMath problems.
13.9
16.7 best
Benchmarks
13 sharedOnly Llama 3.1 70B: 7Only Mistral Small 3.1: 18
Llama 3.1 70B
Mistral Small 3.1