Noometry

Model comparison

GPT-4 vs Grok-2 (Dec 2024)

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.1 on the Noometry Index.

Last verified . 23 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GPT-4 scores higher in 1 category and Grok-2 (Dec 2024) in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok-2 (Dec 2024) leads 48.6 to 34.9.
  • The biggest single-benchmark swing is MATH Level 5: 23% for GPT-4 and 63.5% for Grok-2 (Dec 2024).

Side by side

GPT-4Grok-2 (Dec 2024)
ProviderOpenAIxAI
Noometry Index29.133.7
Released2023-03-142024-08-13
WeightsProprietaryProprietary
Context window8K—
Max output8K—
Input $ / M tokens$30—
Output $ / M tokens$60—
Results tracked3834

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

Category by category

Coding Grok-2 (Dec 2024) leads

GPT-4: 31.6 (#283), Grok-2 (Dec 2024): 33.3 (#258)

BenchmarkGPT-4Grok-2 (Dec 2024)
WeirdML12.4%22.2%
LMArena Coding12541287
BigCodeBench Instruct46%—
LiveBench Coding—46.4%
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Grok-2 (Dec 2024): —

BenchmarkGPT-4Grok-2 (Dec 2024)
METR Time Horizons36.1%—

Reasoning Too close to call

GPT-4: 17.8 (#289), Grok-2 (Dec 2024): 16.9 (#299)

BenchmarkGPT-4Grok-2 (Dec 2024)
LMArena Hard Prompts12411272
DTBench62.7%65.2%
Epoch Capabilities Index125.89130.48
SimpleBench—22.7%
Chess Puzzles4%—
LiveBench Reasoning—54.8%
Mystery Game Puzzles12%—
LiveBench Data Analysis—54.5%
LMCA17.1%—
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
LiveBench—54.3%
WinoGrande87.5%—

Math Grok-2 (Dec 2024) leads

GPT-4: 10.8 (#309), Grok-2 (Dec 2024): 20.8 (#284)

BenchmarkGPT-4Grok-2 (Dec 2024)
OTIS Mock AIME 2024-20251.1%11.5%
LMArena Math12691283
MATH Level 523%63.5%
LiveBench Math—54.9%
FrontierMath (Feb 2025 set)—0.7%
GSM8K92%—

Knowledge Grok-2 (Dec 2024) leads

GPT-4: 18.4 (#282), Grok-2 (Dec 2024): 29.8 (#233)

BenchmarkGPT-4Grok-2 (Dec 2024)
GPQA Diamond35.7%53.8%
LMArena Expert12111254
Confabulations—20.1%
MMLU86.4%—
TriviaQA84.8%—

Multilingual Grok-2 (Dec 2024) leads

GPT-4: 40.6 (#215), Grok-2 (Dec 2024): 43.1 (#188)

BenchmarkGPT-4Grok-2 (Dec 2024)
LMArena Non-English12461282
LMArena Chinese12421289
LMArena French12831318
LMArena German12511287
LMArena Japanese12091244
LMArena Korean11841237
LMArena Russian12511286
LMArena Spanish12611281

Instruction Following Grok-2 (Dec 2024) leads

GPT-4: 65.3 (#222), Grok-2 (Dec 2024): 66.9 (#202)

BenchmarkGPT-4Grok-2 (Dec 2024)
LMArena Instruction Following12411270
LiveBench Instruction Following—69.6%

Long Context Grok-2 (Dec 2024) leads

GPT-4: 37.7 (#212), Grok-2 (Dec 2024): 38.8 (#190)

BenchmarkGPT-4Grok-2 (Dec 2024)
LMArena Longer Query12441276

Writing & Preference Grok-2 (Dec 2024) leads

GPT-4: 34.9 (#268), Grok-2 (Dec 2024): 48.6 (#198)

BenchmarkGPT-4Grok-2 (Dec 2024)
LMArena Text12631305
LMArena Creative Writing12441284
LMArena Multi-Turn12571290
Short-Story Creative Writing—63.6%
EQ-Bench Creative Writing752—
LiveBench Language—45.6%

Frequently asked questions

Is GPT-4 better than Grok-2 (Dec 2024)?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.1 on the Noometry Index.

Is GPT-4 or Grok-2 (Dec 2024) better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 31.6 in the Noometry coding category.

How many benchmarks do GPT-4 and Grok-2 (Dec 2024) share?

23 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok-2 (Dec 2024) has 34.

Related comparisons

Go deeper