Grok 4 Fast Non Reasoning

Grok 4 Fast Non Reasoning is a model from xAI. It has 7 scored results in 5 categories. It has no index.

  • Input: text
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.75%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.1407±8 #147Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted31.8—
CodingCode writing and repair.2 counted34.8—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.1 counted37.7—
KnowledgeFacts and expert knowledge.2 counted33.6—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted30.1—

Results

7 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
AIMEMath33.3% ±1.172 / 95
GPQA Diamond · Vals AIKnowledge62.1% ±2.4108 / 135
IOI v1Coding3.8% ±2.850 / 61
LiveCodeBenchCoding46.1% ±1.1120 / 142
MMMU ProMultimodal63.4% ±1.279 / 92
MMLU ProKnowledge70.3% ±0.4117 / 135
Terminal-Bench 1.0Agentic18.8% ±4.442 / 47
TaxEval v2Finance71.6% ±0.876 / 143
MedScribeHealthcare79.7% ±1.961 / 109
CorpFin v2Finance58.4% ±1.083 / 131
LegalBenchLegal78.4% ±0.5102 / 149
MGSMMultilingual88.0% ±2.054 / 74
MedQAHealthcare75.4% ±0.480 / 95
MedCodeHealthcare30.0% ±2.096 / 106
MortgageTaxFinance25.3% ±0.995 / 97

Sources

BenchLMCC BY-NC 4.0Vals AINo licence stated

More from xAI

All models
Grok 4.769.1Grok 4.667.8Grok 4.563.7Grok 4.20 (Reasoning)55.5Grok 4.353.3