Llama 3.3 70B vs Mistral Large 2

Change models
IndexAll categories, out of 100.
28.1 ±5.3 best
27.4 ±8.9
GapIndex points below the top.
Top
−0.7 · no clear gap
CoverageIndex weight that has results.
90% best
65%
SpeedOutput tokens per second.
—
39/s
EloLMArena rating and rank.
—
1266
ReleasedMonth of release.
2024-12
2024-07
Input / 1MUS dollars per 1M input tokens.
—
$2.00
Output / 1MUS dollars per 1M output tokens.
—
$6.00
1K chats2K tokens in, 500 out, each.
—
$7.00
1K documents20K tokens in, 1K out, each.
—
$46.00
1K agent tasks200K tokens in, 20K out, each.
—
$520.00
ContextMaximum tokens in one request.
128K
131K best
AgenticMulti-step tasks with tools.
27.3 best
23.2
CodingCode writing and repair.
28.8
—
ReasoningLogic problems and puzzles.
27.4
36.7 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
29.0 best
28.7
MultilingualTasks in many languages.
34.0
—
InstructionTasks with strict prompt rules.
40.8 best
18.3
MathMath problems.
15.5
21.9 best

Benchmarks

8 shared
Only Llama 3.3 70B: 8Only Mistral Large 2: 3
Llama 3.3 70B
Mistral Large 2
3.6% best210 / 222
3.3%216 / 222
47.4%155 / 217
50.2% best146 / 217
0.0%150 / 214
0.0%150 / 214
5.1%169 / 200
8.1% best157 / 200
49.8% best174 / 199
48.6%178 / 199
26.6%116 / 149
30.7% best112 / 149
47.1% best84 / 146
31.2%132 / 146
41.6%57 / 88
47.6% best50 / 88