Inference
EN

Llama4 Maverick Instruct Basic vs Grok 4.1 Fast Non Reasoning

Change models
Llama4 Maverick Instruct BasicMeta
Grok 4.1 Fast Non ReasoningxAI
IndexAll categories, out of 100.
36.0 ±8.2
36.2 ±8.2 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
75%
75%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
—
—
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.
—
—
AgenticMulti-step tasks with tools.
29.4
35.5 best
CodingCode writing and repair.
28.5
34.3 best
ReasoningLogic problems and puzzles.
—
—
MultimodalTasks with images and text.
48.5 best
38.1
KnowledgeFacts and expert knowledge.
42.7 best
38.1
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
30.3 best
27.3

Benchmarks

15 shared
Only Llama4 Maverick Instruct Basic: 1Only Grok 4.1 Fast Non Reasoning: 2
Llama4 Maverick Instruct Basic
Grok 4.1 Fast Non Reasoning
LegalBenchLegal
77.8%106 / 149
79.1% best98 / 149
TaxEval v2Finance
66.6% best110 / 143
61.9%121 / 143
LiveCodeBenchCoding
47.3% best118 / 142
42.6%126 / 142
GPQA Diamond · Vals AIKnowledge
69.4% best95 / 135
65.2%102 / 135
MMLU ProKnowledge
79.4% best95 / 135
75.2%112 / 135
CorpFin v2Finance
49.7%109 / 131
52.5% best101 / 131
MedScribeHealthcare
54.2%107 / 109
77.5% best69 / 109
MedCodeHealthcare
36.5% best77 / 106
28.3%99 / 106
MortgageTaxFinance
58.5% best70 / 97
34.3%93 / 97
AIMEMath
25.2%78 / 95
27.1% best75 / 95
MedQAHealthcare
43.3%94 / 95
76.0% best79 / 95
MMMU ProMultimodal
71.7% best67 / 92
63.7%78 / 92
MGSMMultilingual
92.4% best18 / 74
87.6%59 / 74
Terminal-Bench 2.0 · Vals AIAgentic
2.2%65 / 66
18.0% best59 / 66
Terminal-Bench 1.0Agentic
17.5%43 / 47
21.3% best38 / 47