Grok 4 Fast (Reasoning)

Grok 4 Fast (Reasoning) is a reasoning model from xAI in the Grok 4 Fast family. 21 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.45.9 ±4.0
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.2M
EloLMArena rating and rank.1399 (#143)

50 is the middle of the board. The range shows the doubt in the index.

17,975 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
41.5
CodingCode writing and repair.
44.7
ReasoningLogic problems and puzzles.
49.0
MultimodalTasks with images and text.
44.2
KnowledgeFacts and expert knowledge.
48.4
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
40.4
MathMath problems.
56.3

Results

21 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
AIMEMath91.3%56.316 Apr 2026Vals AI
MGSMMultilingual90.9%9 Jan 2026Vals AI
GPQA DiamondKnowledge85.4%57.01 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge84.7%55.4Artificial Analysis
MMLU ProKnowledge79.7%46.11 Sept 2026Vals AI
LiveCodeBenchCoding79.0%56.11 Sept 2026Vals AI
Artificial Analysis Long Context ReasoningReasoning73.7%59.2Artificial Analysis
MMMU ProMultimodal72.8%45.81 Sept 2026Vals AI
τ²-Bench Tool-Agent-User EvaluationAgentic65.8%46.0Victor Barres et al.
Artificial Analysis MMMU-ProMultimodal61.8%42.6Artificial Analysis
Artificial Analysis IFBenchInstruction50.5%40.4Artificial Analysis
ARC-AGI-1 (semi-private)Reasoning48.5%50.1ARC Prize Foundation
SWE-benchCoding45.4%33.91 Sept 2026Vals AI
Terminal-Bench 2.0Agentic29.2%43.54 Jun 2026Vals AI
Terminal-Bench 1.0Agentic27.5%34.912 Jan 2026Vals AI
Artificial Analysis Omniscience AccuracyKnowledge22.8%42.1Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge19.1%45.3Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge17.9%44.8Artificial Analysis
IOI v1Coding11.5%46.59 Aug 2026Vals AI
ARC-AGI-2 (semi-private)Reasoning5.3%42.4ARC Prize Foundation
Critical Physics TasksReasoning2.9%44.5Artificial Analysis
Vibe Code Bench v1.1Coding0.0%42.2OpenHands21 Sept 2026Vals AI

21 benchmarks count, from 21 of 22 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AIARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial use

More from xAI

Grok 4.671.8Grok 4.770.1Grok 4.566.0Grok 4.356.0Grok 4.20 (Reasoning)56.9