GPT-4.1 mini vs Llama4 Maverick Instruct Basic

Change models
IndexAll categories, out of 100.
34.6 ±3.7
35.9 ±8.2 best
GapIndex points below the top.
−1.3 · no clear gap
Top
CoverageIndex weight that has results.
95% best
75%
SpeedOutput tokens per second.
89/s
—
EloLMArena rating and rank.
1340
—
ReleasedMonth of release.
2025-04
—
Input / 1MUS dollars per 1M input tokens.
$0.40
—
Output / 1MUS dollars per 1M output tokens.
$1.60
—
Batch output / 1MBatch price per 1M output tokens.
$0.80
—
1K chats2K tokens in, 500 out, each.
$1.60
—
1K documents20K tokens in, 1K out, each.
$9.60
—
1K agent tasks200K tokens in, 20K out, each.
$112.00
—
ContextMaximum tokens in one request.
1.05M
—
AgenticMulti-step tasks with tools.
35.7 best
29.6
CodingCode writing and repair.
28.3
28.4 best
ReasoningLogic problems and puzzles.
36.8
—
MultimodalTasks with images and text.
39.0
48.0 best
KnowledgeFacts and expert knowledge.
36.2
42.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
33.2
—
MathMath problems.
36.1 best
30.1

Benchmarks

12 shared
Only GPT-4.1 mini: 31Only Llama4 Maverick Instruct Basic: 4
GPT-4.1 mini
Llama4 Maverick Instruct Basic
78.0% best104 / 149
77.8%106 / 149
TaxEval v2Finance
71.9% best70 / 143
66.6%110 / 143
58.2% best109 / 142
47.3%118 / 142
67.9%99 / 135
69.4% best95 / 135
MMLU ProKnowledge
77.2%105 / 135
79.4% best95 / 135
CorpFin v2Finance
57.9% best86 / 131
49.7%109 / 131
65.5% best41 / 97
58.5%70 / 97
AIMEMath
49.4% best63 / 95
25.2%78 / 95
MedQAHealthcare
84.6% best61 / 95
43.3%94 / 95
MMMU ProMultimodal
70.5%70 / 92
71.7% best67 / 92
MGSMMultilingual
87.8%57 / 74
92.4% best18 / 74
88.0% best31 / 59
85.2%35 / 59