Noometry

Model comparison

Gemini 3 Pro vs Grok 4

Gemini 3 Pro is the stronger model overall, scoring 54.8 to 48.1 on the Noometry Index.

Last verified . 43 shared benchmarks.

Gemini 3 Pro Google

54.8

Rank #28 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 43 benchmarks with published results for both. Gemini 3 Pro scores higher in 8 categories and Grok 4 in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in multimodal, where Gemini 3 Pro leads 57.6 to 33.7.
  • The biggest single-benchmark swing is Terminal-Bench: 69.4% for Gemini 3 Pro and 27.2% for Grok 4.

Side by side

Gemini 3 ProGrok 4
ProviderGooglexAI
Noometry Index54.848.1
Released2025-11-182025-07-09
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked6748

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

Category by category

Coding Gemini 3 Pro leads

Gemini 3 Pro: 51.6 (#39), Grok 4: 50.3 (#46)

BenchmarkGemini 3 ProGrok 4
WeirdML69.9%45.7%
LMArena Coding14811408
SWE-bench Verified72.9%—
SWE-bench Verified (bash only)74.2%—
Aider Polyglot—79.6%
LMArena WebDev1440—
SWE-bench Multilingual68.7%—
GSO18.6%—
ALE-Bench1,177—
AlgoTune1.83—

Agentic & Tool Use Gemini 3 Pro leads

Gemini 3 Pro: 40.6 (#23), Grok 4: 32.3 (#68)

BenchmarkGemini 3 ProGrok 4
Terminal-Bench69.4%27.2%
Berkeley Function Calling Leaderboard72.5%63%
GDPval40.3%21.1%
DeepResearch Bench46.3%47.3%
BALROG58.1%43.6%
LMArena Search12071142
METR Time Horizons71%66.6%
Remote Labor Index1.3%—
τ²-bench Airline80.5%—
τ²-bench Banking18%—
τ²-bench Retail75.9%—
τ²-bench Telecom91%—
Cybench—43%
Vending-Bench 25,478—

Reasoning Gemini 3 Pro leads

Gemini 3 Pro: 52.5 (#31), Grok 4: 36.7 (#65)

BenchmarkGemini 3 ProGrok 4
ARC-AGI-231.1%16%
SimpleBench76.4%60.5%
Kagi LLM Benchmark80.1%73.6%
ARC-AGI-175%66.7%
Chess Puzzles31%28%
LMArena Hard Prompts14801409
Epoch Capabilities Index152.92146.44
ForecastBench61.260.9
NYT Connections (extended)94.4%—
CritPt6.9%—
EnigmaEval18.2%—

Math Gemini 3 Pro leads

Gemini 3 Pro: 49.9 (#59), Grok 4: 48.4 (#64)

BenchmarkGemini 3 ProGrok 4
OTIS Mock AIME 2024-202591.4%84%
Omni-MATH55.5%60.3%
LMArena Math14761422
FrontierMath (Feb 2025 set)37.6%19.7%
FrontierMath Tier 4 (v1)18.8%2.1%
MathArena Final-Answer Competitions67%—
ProofBench20%—

Knowledge Gemini 3 Pro leads

Gemini 3 Pro: 64.4 (#16), Grok 4: 53.8 (#55)

BenchmarkGemini 3 ProGrok 4
GPQA Diamond92.6%87%
MMLU-Pro90.3%85.1%
GPQA (HELM)80.3%72.7%
LMArena Expert14751415
Humanity's Last Exam37.5%—
Confabulations—12.4%
Vectara Hallucination Rate13.6%—

Multimodal Gemini 3 Pro leads

Gemini 3 Pro: 57.6 (#2), Grok 4: 33.7 (#94)

BenchmarkGemini 3 ProGrok 4
LMArena Vision13051210
GeoBench84%45%
VPCT91%—
LMArena Document1434—

Multilingual Gemini 3 Pro leads

Gemini 3 Pro: 56.9 (#16), Grok 4: 51.8 (#103)

BenchmarkGemini 3 ProGrok 4
LMArena Non-English14741403
LMArena Chinese15231427
LMArena French14921418
LMArena German15151429
LMArena Japanese15101394
LMArena Korean14481377
LMArena Russian14931410
LMArena Spanish14701420

Instruction Following Grok 4 leads

Gemini 3 Pro: 76.3 (#45), Grok 4: 79.2 (#5)

BenchmarkGemini 3 ProGrok 4
IFEval87.7%94.9%
LMArena Instruction Following14581387

Long Context Grok 4 leads

Gemini 3 Pro: 44.0 (#79), Grok 4: 63.1 (#4)

BenchmarkGemini 3 ProGrok 4
LMArena Longer Query14711409
Fiction.LiveBench—94.4%
CL-bench15.8%—

Writing & Preference Gemini 3 Pro leads

Gemini 3 Pro: 66.4 (#35), Grok 4: 58.5 (#116)

BenchmarkGemini 3 ProGrok 4
LMArena Text14791411
LMArena Creative Writing14821397
WildBench85.9%79.7%
LMArena Multi-Turn14841416
Short-Story Creative Writing—76.9%
EQ-Bench Creative Writing1525—

Frequently asked questions

Is Gemini 3 Pro better than Grok 4?

Gemini 3 Pro is the stronger model overall, scoring 54.8 to 48.1 on the Noometry Index.

Is Gemini 3 Pro or Grok 4 better for coding?

Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 50.3 in the Noometry coding category.

How many benchmarks do Gemini 3 Pro and Grok 4 share?

43 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper