Noometry

Model comparison

Grok 4 vs o4-mini

Grok 4 is the stronger model overall, scoring 48.1 to 41.6 on the Noometry Index.

Last verified . 43 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 43 benchmarks with published results for both. Grok 4 scores higher in 8 categories and o4-mini in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 45.5.
  • The biggest single-benchmark swing is SimpleBench: 60.5% for Grok 4 and 38.7% for o4-mini.

Side by side

Grok 4o4-mini
ProviderxAIOpenAI
Noometry Index48.141.6
Released2025-07-092025-04-16
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$1.10
Output $ / M tokens—$4.40
Results tracked4860

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), o4-mini: 40.9 (#127)

BenchmarkGrok 4o4-mini
Aider Polyglot79.6%72%
WeirdML45.7%52.6%
LMArena Coding14081368
SWE-bench Verified (bash only)—45%
GSO—3.6%
CadEval—62%
ALE-Bench—826.17
AlgoTune—1.72

Agentic & Tool Use Too close to call

Grok 4: 32.3 (#68), o4-mini: 32.6 (#61)

BenchmarkGrok 4o4-mini
Berkeley Function Calling Leaderboard63%53.2%
GDPval21.1%25.3%
METR Time Horizons66.6%63.9%
Terminal-Bench27.2%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), o4-mini: 24.6 (#162)

BenchmarkGrok 4o4-mini
ARC-AGI-216%6.1%
SimpleBench60.5%38.7%
Kagi LLM Benchmark73.6%67.6%
ARC-AGI-166.7%58.7%
Chess Puzzles28%26%
LMArena Hard Prompts14091351
Epoch Capabilities Index146.44145.64
ForecastBench60.961.8
CritPt—0.6%
EnigmaEval—9.2%
Mystery Game Puzzles—5%
DTBench—77.6%
LMCA—26.5%

Math Grok 4 leads

Grok 4: 48.4 (#64), o4-mini: 40.8 (#89)

BenchmarkGrok 4o4-mini
OTIS Mock AIME 2024-202584%81.7%
Omni-MATH60.3%72%
LMArena Math14221389
FrontierMath (Feb 2025 set)19.7%24.8%
FrontierMath Tier 4 (v1)2.1%6.3%
FrontierMath (Tiers 1-3)—36.1%
FrontierMath Tier 4—4.9%
MATH Level 5—97.8%

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), o4-mini: 43.6 (#91)

BenchmarkGrok 4o4-mini
GPQA Diamond87%79.6%
MMLU-Pro85.1%82%
Confabulations12.4%15.8%
GPQA (HELM)72.7%73.5%
LMArena Expert14151343
Humanity's Last Exam—18.1%
SimpleQA Verified—19.6%
Vectara Hallucination Rate—18.6%

Multimodal o4-mini leads

Grok 4: 33.7 (#94), o4-mini: 40.2 (#49)

BenchmarkGrok 4o4-mini
LMArena Vision12101194
GeoBench45%64%
VPCT—57.5%

Multilingual Grok 4 leads

Grok 4: 51.8 (#103), o4-mini: 47.0 (#154)

BenchmarkGrok 4o4-mini
LMArena Non-English14031337
LMArena Chinese14271354
LMArena French14181364
LMArena German14291336
LMArena Japanese13941308
LMArena Korean13771312
LMArena Russian14101334
LMArena Spanish14201347

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), o4-mini: 75.2 (#68)

BenchmarkGrok 4o4-mini
IFEval94.9%92.8%
LMArena Instruction Following13871321

Long Context Grok 4 leads

Grok 4: 63.1 (#4), o4-mini: 45.5 (#33)

BenchmarkGrok 4o4-mini
Fiction.LiveBench94.4%77.8%
LMArena Longer Query14091315

Writing & Preference Grok 4 leads

Grok 4: 58.5 (#116), o4-mini: 54.0 (#152)

BenchmarkGrok 4o4-mini
LMArena Text14111353
LMArena Creative Writing13971294
Short-Story Creative Writing76.9%75%
WildBench79.7%85.4%
LMArena Multi-Turn14161350

Frequently asked questions

Is Grok 4 better than o4-mini?

Grok 4 is the stronger model overall, scoring 48.1 to 41.6 on the Noometry Index.

Is Grok 4 or o4-mini better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 40.9 in the Noometry coding category.

How many benchmarks do Grok 4 and o4-mini share?

43 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper