Noometry

Model comparison

GPT-4 Turbo vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.8 to 30.5 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Grok 4.3 in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.3 leads 46.0 to 9.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 93.3% for Grok 4.3.
  • Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Grok 4.3 accepts more context: 1M tokens versus 128K.

Side by side

GPT-4 TurboGrok 4.3
ProviderOpenAIxAI
Noometry Index30.543.8
Released2023-11-062026-04-17
WeightsProprietaryProprietary
Context window128K1M
Max output4K30K
Input $ / M tokens$10$1.25
Output $ / M tokens$30$2.50
Results tracked3640

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

Category by category

Coding Grok 4.3 leads

GPT-4 Turbo: 33.8 (#249), Grok 4.3: 41.6 (#121)

BenchmarkGPT-4 TurboGrok 4.3
WeirdML18%49.9%
LMArena Coding12681415
LMArena WebDev—1357
SciCode—47.3%
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
ALE-Bench—944.17
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Grok 4.3: 27.7 (#99)

BenchmarkGPT-4 TurboGrok 4.3
GDP.pdf—8%
LMArena Search—1165
METR Time Horizons36.7%—
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

GPT-4 Turbo: 15.3 (#317), Grok 4.3: 35.9 (#68)

BenchmarkGPT-4 TurboGrok 4.3
Chess Puzzles6%25%
LMArena Hard Prompts12511396
DTBench61.6%90.7%
LMCA9.8%38.3%
Epoch Capabilities Index127.25149.16
ForecastBench59.460.3
SimpleBench25.1%—
NYT Connections (extended)—55.2%
CritPt—8%

Math Grok 4.3 leads

GPT-4 Turbo: 9.0 (#322), Grok 4.3: 46.0 (#74)

BenchmarkGPT-4 TurboGrok 4.3
FrontierMath (Tiers 1-3)0.7%42.8%
OTIS Mock AIME 2024-20256.7%93.3%
LMArena Math12721388
FrontierMath Tier 4—14.6%
ProofBench—11%
MATH Level 546.7%—

Knowledge Grok 4.3 leads

GPT-4 Turbo: 24.3 (#268), Grok 4.3: 52.5 (#62)

BenchmarkGPT-4 TurboGrok 4.3
GPQA Diamond46.6%88.8%
LMArena Expert12231385
SimpleQA Verified—33.2%
Confabulations28.4%—
MMLU81.3%—

Multimodal Too close to call

GPT-4 Turbo: 30.6 (#110), Grok 4.3: 31.6 (#104)

BenchmarkGPT-4 TurboGrok 4.3
LMArena Vision10901229
Blueprint-Bench 2—0%

Multilingual Grok 4.3 leads

GPT-4 Turbo: 40.5 (#216), Grok 4.3: 50.5 (#120)

BenchmarkGPT-4 TurboGrok 4.3
LMArena Non-English12451385
LMArena Chinese12421422
LMArena French12761412
LMArena German12591395
LMArena Japanese11941379
LMArena Korean11871356
LMArena Russian12591399
LMArena Spanish12601398

Instruction Following Grok 4.3 leads

GPT-4 Turbo: 65.8 (#216), Grok 4.3: 72.1 (#140)

BenchmarkGPT-4 TurboGrok 4.3
LMArena Instruction Following12491366

Long Context Grok 4.3 leads

GPT-4 Turbo: 38.0 (#206), Grok 4.3: 42.5 (#123)

BenchmarkGPT-4 TurboGrok 4.3
LMArena Longer Query12541393

Writing & Preference Grok 4.3 leads

GPT-4 Turbo: 47.7 (#206), Grok 4.3: 58.5 (#118)

BenchmarkGPT-4 TurboGrok 4.3
LMArena Text12721397
LMArena Creative Writing12691380
LMArena Multi-Turn12671406
EQ-Bench 4—1075

Frequently asked questions

Is GPT-4 Turbo better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo 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 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Grok 4.3 better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Grok 4.3 does, with 1M tokens against 128K.

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

27 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper