Llama 4 Maverick vs Mistral Large 3

Change models
IndexAll categories, out of 100.
34.4 ±4.7 best
34.3 ±4.4
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
61/s
61/s
EloLMArena rating and rank.
—
1429
ReleasedMonth of release.
2025-04
2025-12
Input / 1MUS dollars per 1M input tokens.
$0.35 best
$0.50
Output / 1MUS dollars per 1M output tokens.
$1.00 best
$1.50
1K chats2K tokens in, 500 out, each.
$1.20 best
$1.75
1K documents20K tokens in, 1K out, each.
$8.00 best
$11.50
1K agent tasks200K tokens in, 20K out, each.
$90.00 best
$130.00
ContextMaximum tokens in one request.
524K best
262K
AgenticMulti-step tasks with tools.
36.9 best
29.7
CodingCode writing and repair.
37.2
38.2 best
ReasoningLogic problems and puzzles.
36.7 best
34.4
MultimodalTasks with images and text.
36.0 best
34.5
KnowledgeFacts and expert knowledge.
34.0
38.9 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
29.2 best
22.9
MathMath problems.
28.6
34.3 best

Benchmarks

9 shared
Only Llama 4 Maverick: 10Only Mistral Large 3: 18
Llama 4 Maverick
Mistral Large 3
4.9% best180 / 222
4.2%194 / 222
50.0% best154 / 217
36.0%174 / 217
0.0%150 / 214
0.0%150 / 214
67.1%139 / 199
68.0% best137 / 199
17.8%136 / 149
24.6% best122 / 149
43.0% best94 / 146
36.2%120 / 146
0.0%101 / 133
0.0%101 / 133
31.7%103 / 114
36.6% best98 / 114
62.1% best88 / 113
55.7%95 / 113