Noometry

Model comparison

GPT-4 Turbo vs Grok-3 mini

Grok-3 mini is the stronger model overall, scoring 41.2 to 30.5 on the Noometry Index.

Last verified . 23 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-3 mini leads 42.1 to 9.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 77.8% for Grok-3 mini.

Side by side

GPT-4 TurboGrok-3 mini
ProviderOpenAIxAI
Noometry Index30.541.2
Released2023-11-062025-04-09
WeightsProprietaryProprietary
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked3635

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

Category by category

Coding Grok-3 mini leads

GPT-4 Turbo: 33.8 (#249), Grok-3 mini: 40.8 (#131)

BenchmarkGPT-4 TurboGrok-3 mini
WeirdML18%42.6%
LMArena Coding12681379
Aider Polyglot—49.3%
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Grok-3 mini: —

BenchmarkGPT-4 TurboGrok-3 mini
METR Time Horizons36.7%—

Reasoning GPT-4 Turbo leads

GPT-4 Turbo: 15.3 (#317), Grok-3 mini: 13.6 (#334)

BenchmarkGPT-4 TurboGrok-3 mini
LMArena Hard Prompts12511375
Epoch Capabilities Index127.25140.35
ARC-AGI-2—0.4%
SimpleBench25.1%—
Kagi LLM Benchmark—61.3%
ARC-AGI-1—16.5%
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
ForecastBench59.4—

Math Grok-3 mini leads

GPT-4 Turbo: 9.0 (#322), Grok-3 mini: 42.1 (#85)

BenchmarkGPT-4 TurboGrok-3 mini
OTIS Mock AIME 2024-20256.7%77.8%
LMArena Math12721386
MATH Level 546.7%90.9%
FrontierMath (Tiers 1-3)0.7%—
Omni-MATH—31.8%
FrontierMath (Feb 2025 set)—5.9%

Knowledge Grok-3 mini leads

GPT-4 Turbo: 24.3 (#268), Grok-3 mini: 46.4 (#81)

BenchmarkGPT-4 TurboGrok-3 mini
GPQA Diamond46.6%76.3%
Confabulations28.4%10.8%
LMArena Expert12231395
MMLU-Pro—79.9%
GPQA (HELM)—67.5%
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Grok-3 mini: —

BenchmarkGPT-4 TurboGrok-3 mini
LMArena Vision1090—

Multilingual Grok-3 mini leads

GPT-4 Turbo: 40.5 (#216), Grok-3 mini: 48.1 (#145)

BenchmarkGPT-4 TurboGrok-3 mini
LMArena Non-English12451352
LMArena Chinese12421387
LMArena French12761357
LMArena German12591349
LMArena Japanese11941342
LMArena Korean11871335
LMArena Russian12591353
LMArena Spanish12601381

Instruction Following Grok-3 mini leads

GPT-4 Turbo: 65.8 (#216), Grok-3 mini: 78.5 (#9)

BenchmarkGPT-4 TurboGrok-3 mini
LMArena Instruction Following12491357
IFEval—95.1%

Long Context Grok-3 mini leads

GPT-4 Turbo: 38.0 (#206), Grok-3 mini: 41.0 (#147)

BenchmarkGPT-4 TurboGrok-3 mini
LMArena Longer Query12541372
Fiction.LiveBench—66.7%

Writing & Preference Grok-3 mini leads

GPT-4 Turbo: 47.7 (#206), Grok-3 mini: 52.5 (#169)

BenchmarkGPT-4 TurboGrok-3 mini
LMArena Text12721370
LMArena Creative Writing12691342
LMArena Multi-Turn12671355
Short-Story Creative Writing—73.5%
WildBench—65.1%

Frequently asked questions

Is GPT-4 Turbo better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 30.5 on the Noometry Index.

Is GPT-4 Turbo or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 33.8 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and Grok-3 mini share?

23 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper