Noometry

Model comparison

GPT-4 Turbo vs Grok 4.20 Multi-Agent

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 30.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Grok 4.20 Multi-Agent xAI

45.5

Rank #62 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Grok 4.20 Multi-Agent in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.20 Multi-Agent leads 36.6 to 8.6.
  • Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 128K.

Side by side

GPT-4 TurboGrok 4.20 Multi-Agent
ProviderOpenAIxAI
Noometry Index30.345.5
Released2023-11-062026-03-09
WeightsProprietaryProprietary
Context window128K1M
Max output4K30K
Input $ / M tokens$10$1.25
Output $ / M tokens$30$2.50
Results tracked3620

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

Category by category

Coding Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 33.4 (#247), Grok 4.20 Multi-Agent: 42.4 (#91)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Coding12681458
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Grok 4.20 Multi-Agent: —

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Search—1204
METR Time Horizons36.7%—

Reasoning Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 14.9 (#311), Grok 4.20 Multi-Agent: 42.4 (#44)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Hard Prompts12511448
SimpleBench25.1%—
NYT Connections (extended)—89.6%
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 8.6 (#316), Grok 4.20 Multi-Agent: 36.6 (#106)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Math12721441
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 24.3 (#263), Grok 4.20 Multi-Agent: 39.7 (#116)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Expert12231445
GPQA Diamond46.6%—
Confabulations28.4%—
MMLU81.3%—

Multimodal Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 30.0 (#104), Grok 4.20 Multi-Agent: 39.8 (#44)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Vision10901259

Multilingual Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 40.7 (#211), Grok 4.20 Multi-Agent: 54.6 (#40)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Non-English12451440
LMArena Chinese12421475
LMArena French12751467
LMArena German12591456
LMArena Japanese11941405
LMArena Korean11871416
LMArena Russian12591457
LMArena Spanish12601447

Instruction Following Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 66.0 (#211), Grok 4.20 Multi-Agent: 75.0 (#80)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Instruction Following12501420

Long Context Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 38.0 (#200), Grok 4.20 Multi-Agent: 43.7 (#84)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Longer Query12541430

Writing & Preference Grok 4.20 Multi-Agent leads

GPT-4 Turbo: 47.9 (#201), Grok 4.20 Multi-Agent: 64.1 (#57)

BenchmarkGPT-4 TurboGrok 4.20 Multi-Agent
LMArena Text12721450
LMArena Creative Writing12691435
LMArena Multi-Turn12671451

Frequently asked questions

Is GPT-4 Turbo better than Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 30.3 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent 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 4.20 Multi-Agent better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 33.4 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 Multi-Agent does, with 1M tokens against 128K.

How many benchmarks do GPT-4 Turbo and Grok 4.20 Multi-Agent share?

18 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Grok 4.20 Multi-Agent has 20.

Related comparisons

Go deeper