Inference
EN
xAI

Grok 4.1 Fast (Reasoning)

Grok 4.1 Fast (Reasoning) is a reasoning model from xAI in the Grok 4.1 Fast family. 17 benchmarks count toward its index, in 8 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2025-11
RankedEnough results for an index.
IndexAll categories, out of 100.47.3±3.9Median 51.0
CoverageIndex weight that has results.100%
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.2MMedian 262K
EloLMArena rating and rank.1408±3 #145Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.3 counted48.4144 / 218
CodingCode writing and repair.4 counted43.3168 / 209
ReasoningLogic problems and puzzles.2 counted50.3112 / 227
MultimodalTasks with images and text.1 counted43.6—
KnowledgeFacts and expert knowledge.4 counted48.1149 / 268
MultilingualTasks in many languages.1 counted59.5—
InstructionTasks with strict prompt rules.1 counted38.3—
MathMath problems.1 counted55.7—

Results

17 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
EuroEval SwedishMultilingualAbove fitFar above this model's index.68.3% ±0.613 / 195
EuroEval DutchMultilingual63.8% ±0.414 / 175
EuroEval SpanishMultilingual59.8% ±0.516 / 176
EuroEval ItalianMultilingual66.1% ±0.416 / 174
EuroEval PortugueseMultilingual64.8% ±0.517 / 182
EuroEval GermanMultilingual54.8% ±0.621 / 191
EuroEval PolishMultilingual57.6% ±0.427 / 209
EuroEval FrenchMultilingual65.4% ±0.424 / 178
τ²-Bench Tool-Agent-User EvaluationAgentic93.3%32 / 149
AIMEMath91.9% ±0.621 / 95
GPQA Diamond · Vals AIKnowledge84.3% ±1.951 / 135
Artificial Analysis GPQA DiamondKnowledge85.3%77 / 199
Artificial Analysis Long Context ReasoningReasoning74.0%99 / 217
Critical Physics TasksReasoning2.9%98 / 214
LiveCodeBenchCoding80.6% ±1.166 / 142
MMLU ProKnowledge84.2% ±0.464 / 135
Artificial Analysis Humanity's Last ExamKnowledge19.3%114 / 222
Artificial Analysis IFBenchInstruction52.7%77 / 146
Artificial Analysis Omniscience AccuracyKnowledge25.1%104 / 164
MMMU ProMultimodal72.7% ±1.162 / 92
Terminal-Bench 1.0Agentic28.8% ±5.133 / 47
Artificial Analysis MMLU-ProKnowledge85.4%11 / 15
Artificial Analysis LiveCodeBenchCoding82.2%9 / 12
Artificial Analysis MMMU-ProMultimodal63.3%85 / 113
Terminal-Bench 2.0 · Vals AIAgentic24.7% ±4.652 / 66
IOI v1Coding3.1% ±1.752 / 61
Vibe Code Bench v1.1Coding1.2% ±1.2118 / 123
SWE-benchCoding41.4% ±2.284 / 87
CorpFin v2Finance66.0% ±0.923 / 131
TaxEval v2Finance73.1% ±0.952 / 143
MedQAHealthcare92.1% ±0.235 / 95
Finance Agent v1.1Finance52.4% ±2.823 / 51
CaseLaw v2Legal60.5% ±0.824 / 53
LegalBenchLegal82.5% ±0.569 / 149
MedScribeHealthcare78.7% ±1.964 / 109
MGSMMultilingual89.5% ±1.945 / 74
MortgageTaxFinance42.6% ±1.089 / 97
SAGEEducation74.5% ±2.227 / 29
MedCodeHealthcare28.1% ±2.0100 / 106
Public Benefits Bench v1.1Public benefits44.8% ±1.348 / 50
Public Benefits Bench v1Public benefits44.3% ±1.313 / 13

Sources

BenchLMCC BY-NC 4.0Vals AINo licence statedEuroEvalMIT

History

5 releases
Index48.3 → 47.3
23 Oct 202612 Nov 2026

Questions

How good is Grok 4.1 Fast (Reasoning)?
Its index is 47.3 out of 100. That is place 166 of 283 ranked models.
What is Grok 4.1 Fast (Reasoning) best at?
Reasoning: 50.3 out of 100, place 112 of 227.
What is the context window of Grok 4.1 Fast (Reasoning)?
2M tokens.
Is Grok 4.1 Fast (Reasoning) open source?
No. Its weights are not published.
When was Grok 4.1 Fast (Reasoning) released?
November 2025.

Badge

Grok 4.1 Fast (Reasoning) on Inference360: place 166 of 283, index 47.3
HTML
<a href="https://inference360.ai/models/grok-4-1-fast-reasoning"><img src="https://inference360.ai/badges/grok-4-1-fast-reasoning.svg" alt="Grok 4.1 Fast (Reasoning) on Inference360: place 166 of 283, index 47.3" height="20"></a>
Markdown
[![Grok 4.1 Fast (Reasoning) on Inference360: place 166 of 283, index 47.3](https://inference360.ai/badges/grok-4-1-fast-reasoning.svg)](https://inference360.ai/models/grok-4-1-fast-reasoning)

Compare with

MiMo-V2-Omni47.2Claude Opus 4.147.5Claude 4 Opus Thinking47.0Grok 4 Fast (Reasoning)45.3Grok 4.1 Fast33.3

More from xAI

All models
Grok 4.1 Fast33.3Grok 4.1UnrankedGrok RealtimeUnrankedGrok 4 Fast (Reasoning)45.3Grok Code Fast 141.2