Noometry

Model comparison

Grok 3 vs Grok 4.1 Fast

Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 39.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Grok 3 xAI

39.9

Rank #157 Confirmed

Grok 4.1 Fast xAI

41.4

Rank #136 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Grok 3 scores higher in 5 categories and Grok 4.1 Fast in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.1 Fast leads 43.4 to 13.7.
  • The biggest single-benchmark swing is SimpleBench: 36.1% for Grok 3 and 56% for Grok 4.1 Fast.

Side by side

Grok 3Grok 4.1 Fast
ProviderxAIxAI
Noometry Index39.941.4
Released2025-04-092025-06-27
WeightsProprietaryProprietary
Context window—128K
Max output—30K
Input $ / M tokens—$0.20
Output $ / M tokens—$0.50
Results tracked4032

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Grok 3 leads

Grok 3: 41.9 (#115), Grok 4.1 Fast: 34.1 (#245)

BenchmarkGrok 3Grok 4.1 Fast
LMArena Coding14321411
Aider Polyglot53.3%—
LMArena WebDev—1242
WeirdML37.2%—
ALE-Bench—394.93

Agentic & Tool Use Grok 4.1 Fast leads

Grok 3: 30.5 (#76), Grok 4.1 Fast: 36.3 (#39)

BenchmarkGrok 3Grok 4.1 Fast
Berkeley Function Calling Leaderboard—69.6%
τ²-bench Banking—13.1%
BALROG29.5%—
LMArena Search—1171
Vending-Bench 2—1,107

Reasoning Grok 4.1 Fast leads

Grok 3: 13.7 (#333), Grok 4.1 Fast: 43.4 (#49)

BenchmarkGrok 3Grok 4.1 Fast
SimpleBench36.1%56%
LMArena Hard Prompts14341407
ARC-AGI-20%—
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—87.4%
ARC-AGI-15.5%—
DTBench—87.7%
Epoch Capabilities Index138.33—
ForecastBench—61

Math Grok 3 leads

Grok 3: 38.0 (#145), Grok 4.1 Fast: 31.9 (#221)

BenchmarkGrok 3Grok 4.1 Fast
LMArena Math13911408
MathArena Final-Answer Competitions—60.9%
OTIS Mock AIME 2024-202555.6%—
ProofBench—4%
Omni-MATH46.4%—
MATH Level 588.7%—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 3 leads

Grok 3: 46.2 (#82), Grok 4.1 Fast: 33.1 (#207)

BenchmarkGrok 3Grok 4.1 Fast
Vectara Hallucination Rate5.8%17.8%
LMArena Expert14211399
GPQA Diamond75.8%—
MMLU-Pro78.8%—
Confabulations14.2%—
GPQA (HELM)65%—

Multimodal Not comparable

Grok 3: —, Grok 4.1 Fast: 37.0 (#76)

BenchmarkGrok 3Grok 4.1 Fast
LMArena Vision—1201

Multilingual Grok 3 leads

Grok 3: 52.3 (#87), Grok 4.1 Fast: 51.0 (#114)

BenchmarkGrok 3Grok 4.1 Fast
LMArena Non-English14101391
LMArena Chinese14481441
LMArena French14601415
LMArena German14311404
LMArena Japanese13871349
LMArena Korean13731361
LMArena Russian14161387
LMArena Spanish14171413

Instruction Following Grok 3 leads

Grok 3: 75.0 (#73), Grok 4.1 Fast: 72.7 (#133)

BenchmarkGrok 3Grok 4.1 Fast
LMArena Instruction Following14091376
IFEval88.4%—

Long Context Grok 4.1 Fast leads

Grok 3: 38.7 (#192), Grok 4.1 Fast: 42.4 (#126)

BenchmarkGrok 3Grok 4.1 Fast
LMArena Longer Query14391390
Fiction.LiveBench58.3%—

Writing & Preference Grok 4.1 Fast leads

Grok 3: 55.8 (#141), Grok 4.1 Fast: 57.2 (#131)

BenchmarkGrok 3Grok 4.1 Fast
LMArena Text14261408
LMArena Creative Writing14141394
EQ-Bench Creative Writing11861327
LMArena Multi-Turn14251389
Short-Story Creative Writing76.4%—
WildBench84.9%—

Frequently asked questions

Is Grok 3 better than Grok 4.1 Fast?

Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 39.9 on the Noometry Index.

Is Grok 3 or Grok 4.1 Fast better for coding?

Grok 3 scores higher on coding benchmarks: 41.9 versus 34.1 in the Noometry coding category.

How many benchmarks do Grok 3 and Grok 4.1 Fast share?

20 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Grok 4.1 Fast has 32.

Related comparisons

Go deeper