Noometry

Model comparison

GPT-4 vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.8 to 29.1 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Grok 4.3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.3 leads 46.0 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 93.3% for Grok 4.3.
  • Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $30 / $60 for GPT-4.
  • Grok 4.3 accepts more context: 1M tokens versus 8K.

Side by side

GPT-4Grok 4.3
ProviderOpenAIxAI
Noometry Index29.143.8
Released2023-03-142026-04-17
WeightsProprietaryProprietary
Context window8K1M
Max output8K30K
Input $ / M tokens$30$1.25
Output $ / M tokens$60$2.50
Results tracked3840

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

Category by category

Coding Grok 4.3 leads

GPT-4: 31.6 (#283), Grok 4.3: 41.6 (#121)

BenchmarkGPT-4Grok 4.3
WeirdML12.4%49.9%
LMArena Coding12541415
LMArena WebDev—1357
SciCode—47.3%
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
ALE-Bench—944.17
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Grok 4.3: 27.7 (#99)

BenchmarkGPT-4Grok 4.3
GDP.pdf—8%
LMArena Search—1165
METR Time Horizons36.1%—
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

GPT-4: 17.8 (#289), Grok 4.3: 35.9 (#68)

BenchmarkGPT-4Grok 4.3
Chess Puzzles4%25%
LMArena Hard Prompts12411396
DTBench62.7%90.7%
LMCA17.1%38.3%
Epoch Capabilities Index125.89149.16
ForecastBench57.860.3
NYT Connections (extended)—55.2%
CritPt—8%
Mystery Game Puzzles12%—
BIG-Bench Hard75.1%—
HellaSwag95.3%—
WinoGrande87.5%—

Math Grok 4.3 leads

GPT-4: 10.8 (#309), Grok 4.3: 46.0 (#74)

BenchmarkGPT-4Grok 4.3
OTIS Mock AIME 2024-20251.1%93.3%
LMArena Math12691388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
ProofBench—11%
MATH Level 523%—
GSM8K92%—

Knowledge Grok 4.3 leads

GPT-4: 18.4 (#282), Grok 4.3: 52.5 (#62)

BenchmarkGPT-4Grok 4.3
GPQA Diamond35.7%88.8%
LMArena Expert12111385
SimpleQA Verified—33.2%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Grok 4.3: 31.6 (#104)

BenchmarkGPT-4Grok 4.3
LMArena Vision—1229
Blueprint-Bench 2—0%

Multilingual Grok 4.3 leads

GPT-4: 40.6 (#215), Grok 4.3: 50.5 (#120)

BenchmarkGPT-4Grok 4.3
LMArena Non-English12461385
LMArena Chinese12421422
LMArena French12831412
LMArena German12511395
LMArena Japanese12091379
LMArena Korean11841356
LMArena Russian12511399
LMArena Spanish12611398

Instruction Following Grok 4.3 leads

GPT-4: 65.3 (#222), Grok 4.3: 72.1 (#140)

BenchmarkGPT-4Grok 4.3
LMArena Instruction Following12411366

Long Context Grok 4.3 leads

GPT-4: 37.7 (#212), Grok 4.3: 42.5 (#123)

BenchmarkGPT-4Grok 4.3
LMArena Longer Query12441393

Writing & Preference Grok 4.3 leads

GPT-4: 34.9 (#268), Grok 4.3: 58.5 (#118)

BenchmarkGPT-4Grok 4.3
LMArena Text12631397
LMArena Creative Writing12441380
LMArena Multi-Turn12571406
EQ-Bench Creative Writing752—
EQ-Bench 4—1075

Frequently asked questions

Is GPT-4 better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Grok 4.3?

Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Grok 4.3 better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Grok 4.3 does, with 1M tokens against 8K.

How many benchmarks do GPT-4 and Grok 4.3 share?

25 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper