Noometry

Model comparison

GPT-4.1 vs Grok-3 mini

Grok-3 mini is the stronger model overall, scoring 41.2 to 35.9 on the Noometry Index.

Last verified . 33 shared benchmarks.

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 33 benchmarks with published results for both. GPT-4.1 scores higher in 2 categories and Grok-3 mini in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-3 mini leads 42.1 to 22.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 77.8% for Grok-3 mini.

Side by side

GPT-4.1Grok-3 mini
ProviderOpenAIxAI
Noometry Index35.941.2
Released2025-04-142025-04-09
WeightsProprietaryProprietary
Context window1.05M—
Max output33K—
Input $ / M tokens$2—
Output $ / M tokens$8—
Results tracked5235

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

Category by category

Coding Grok-3 mini leads

GPT-4.1: 34.4 (#238), Grok-3 mini: 40.8 (#131)

BenchmarkGPT-4.1Grok-3 mini
Aider Polyglot52.4%49.3%
WeirdML39%42.6%
LMArena Coding13911379
SWE-bench Verified48.5%—
SWE-bench Verified (bash only)39.6%—
CadEval42%—
ALE-Bench558.1—

Agentic & Tool Use Not comparable

GPT-4.1: 34.7 (#43), Grok-3 mini: —

BenchmarkGPT-4.1Grok-3 mini
Berkeley Function Calling Leaderboard54%—

Reasoning Grok-3 mini leads

GPT-4.1: 11.7 (#339), Grok-3 mini: 13.6 (#334)

BenchmarkGPT-4.1Grok-3 mini
ARC-AGI-20.4%0.4%
Kagi LLM Benchmark52.3%61.3%
ARC-AGI-15.5%16.5%
LMArena Hard Prompts13841375
Epoch Capabilities Index136.78140.35
SimpleBench27%—
Chess Puzzles6%—
EnigmaEval2.2%—
DTBench68.3%—
LMCA25.6%—
ForecastBench61.5—

Math Grok-3 mini leads

GPT-4.1: 22.3 (#280), Grok-3 mini: 42.1 (#85)

BenchmarkGPT-4.1Grok-3 mini
OTIS Mock AIME 2024-202538.3%77.8%
Omni-MATH47.1%31.8%
LMArena Math13701386
MATH Level 583%90.9%
FrontierMath (Feb 2025 set)5.5%5.9%
FrontierMath (Tiers 1-3)6%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok-3 mini leads

GPT-4.1: 37.1 (#160), Grok-3 mini: 46.4 (#81)

BenchmarkGPT-4.1Grok-3 mini
GPQA Diamond66.9%76.3%
MMLU-Pro81.1%79.9%
GPQA (HELM)65.9%67.5%
LMArena Expert13641395
Humanity's Last Exam5.4%—
SimpleQA Verified31.1%—
Confabulations—10.8%
Vectara Hallucination Rate5.6%—

Multimodal Not comparable

GPT-4.1: 38.2 (#67), Grok-3 mini: —

BenchmarkGPT-4.1Grok-3 mini
LMArena Vision1211—
GeoBench72%—

Multilingual GPT-4.1 leads

GPT-4.1: 49.4 (#133), Grok-3 mini: 48.1 (#145)

BenchmarkGPT-4.1Grok-3 mini
LMArena Non-English13701352
LMArena Chinese13821387
LMArena French13821357
LMArena German13811349
LMArena Japanese13191342
LMArena Korean13391335
LMArena Russian13771353
LMArena Spanish13761381

Instruction Following Grok-3 mini leads

GPT-4.1: 71.3 (#153), Grok-3 mini: 78.5 (#9)

BenchmarkGPT-4.1Grok-3 mini
IFEval83.8%95.1%
LMArena Instruction Following13671357

Long Context Too close to call

GPT-4.1: 40.0 (#163), Grok-3 mini: 41.0 (#147)

BenchmarkGPT-4.1Grok-3 mini
Fiction.LiveBench63.9%66.7%
LMArena Longer Query13851372

Writing & Preference GPT-4.1 leads

GPT-4.1: 57.6 (#125), Grok-3 mini: 52.5 (#169)

BenchmarkGPT-4.1Grok-3 mini
LMArena Text13831370
LMArena Creative Writing13631342
WildBench85.4%65.1%
LMArena Multi-Turn13981355
Short-Story Creative Writing—73.5%
EQ-Bench Creative Writing1420—

Frequently asked questions

Is GPT-4.1 better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 35.9 on the Noometry Index.

Is GPT-4.1 or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 34.4 in the Noometry coding category.

How many benchmarks do GPT-4.1 and Grok-3 mini share?

33 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper