Noometry

Model comparison

Grok 4 Fast vs Qwen2.5 72B Instruct

Grok 4 Fast is the stronger model overall, scoring 39.4 to 31.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok 4 Fast xAI

39.4

Rank #167 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok 4 Fast scores higher in 7 categories and Qwen2.5 72B Instruct in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 Fast leads 63.2 to 38.9.
  • The biggest single-benchmark swing is WeirdML: 42.9% for Grok 4 Fast and 16% for Qwen2.5 72B Instruct.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Grok 4 FastQwen2.5 72B Instruct
ProviderxAIAlibaba (Qwen)
Noometry Index39.431.9
Released2025-09-192024-09
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$1.40
Output $ / M tokens—$5.60
Results tracked3043

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

Category by category

Coding Too close to call

Grok 4 Fast: 32.5 (#271), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
WeirdML42.9%16%
LMArena Coding14291292
LMArena WebDev1159—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%

Agentic & Tool Use Grok 4 Fast leads

Grok 4 Fast: 29.5 (#86), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
TheAgentCompany—5.7%
τ²-bench Banking15.7%—
Cybench30%—
BALROG—16.2%
LMArena Search1171—
METR Time Horizons—35.8%

Reasoning Too close to call

Grok 4 Fast: 22.2 (#201), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
LMArena Hard Prompts14121271
DTBench82.7%62.9%
Epoch Capabilities Index144.2129
ForecastBench60.557.5
ARC-AGI-25.3%—
Kagi LLM Benchmark66.1%—
ARC-AGI-148.5%—
LMCA—13.4%
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Grok 4 Fast leads

Grok 4 Fast: 38.9 (#123), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
LMArena Math14191283
OTIS Mock AIME 2024-2025—8.1%
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge Grok 4 Fast leads

Grok 4 Fast: 32.0 (#214), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
LMArena Expert14111245
GPQA Diamond—49.1%
MMLU-Pro—63.1%
Confabulations—19.1%
Vectara Hallucination Rate19.7%—
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multilingual Grok 4 Fast leads

Grok 4 Fast: 51.3 (#111), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
LMArena Non-English13961252
LMArena Chinese14571272
LMArena French14311280
LMArena German13831234
LMArena Japanese13521180
LMArena Korean13571188
LMArena Russian13891264
LMArena Spanish14151256

Instruction Following Grok 4 Fast leads

Grok 4 Fast: 73.2 (#121), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
LMArena Instruction Following13871254
IFEval—80.6%

Long Context Grok 4 Fast leads

Grok 4 Fast: 63.2 (#3), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
LMArena Longer Query14151282
Fiction.LiveBench94.4%—

Writing & Preference Grok 4 Fast leads

Grok 4 Fast: 60.0 (#102), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkGrok 4 FastQwen2.5 72B Instruct
LMArena Text14071269
LMArena Creative Writing13871221
LMArena Multi-Turn14141272
WildBench—80.2%

Frequently asked questions

Is Grok 4 Fast better than Qwen2.5 72B Instruct?

Grok 4 Fast is the stronger model overall, scoring 39.4 to 31.9 on the Noometry Index.

Is Grok 4 Fast or Qwen2.5 72B Instruct better for coding?

They score almost the same on coding (32.5 vs 33.2); test both on your own repository before choosing.

How many benchmarks do Grok 4 Fast and Qwen2.5 72B Instruct share?

21 benchmarks have published results for both models. Grok 4 Fast has 30 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper