Noometry

Model comparison

Grok 4.7 vs Qwen2-72B

Grok 4.7 is the stronger model overall, scoring 53.1 to 30.0 on the Noometry Index.

Last verified . 16 shared benchmarks.

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Grok 4.7 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.7 leads 62.8 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 92.7% for Grok 4.7 and 40.8% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Grok 4.7Qwen2-72B
ProviderxAIAlibaba (Qwen)
Noometry Index53.130.0
Released2026-09-212024-06-07
WeightsProprietaryOpen
Context window500K—
Max output500K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked3926

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

Category by category

Coding Grok 4.7 leads

Grok 4.7: 58.0 (#18), Qwen2-72B: 29.1 (#310)

BenchmarkGrok 4.7Qwen2-72B
LMArena Coding14271196
FrontierCode47.6%—
CursorBench46.3%—
LMArena WebDev1639—
FrontierSWE29.5%—
SciCode57.8%—
WeirdML—11.3%
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%

Agentic & Tool Use Grok 4.7 leads

Grok 4.7: 36.7 (#37), Qwen2-72B: 17.0 (#146)

BenchmarkGrok 4.7Qwen2-72B
APEX-Agents54.6%—
TheAgentCompany—1.1%
GDP.pdf22.8%—
METR Time Horizons—29.9%
Vending-Bench 210,537—

Reasoning Grok 4.7 leads

Grok 4.7: 49.1 (#40), Qwen2-72B: 23.2 (#181)

BenchmarkGrok 4.7Qwen2-72B
LMArena Hard Prompts14131191
Epoch Capabilities Index153.53125.28
NYT Connections (extended)76.8%—
CritPt18%—
Chess Puzzles38%—
Mystery Game Puzzles29%—
DTBench96%—
LMCA49.4%—

Math Grok 4.7 leads

Grok 4.7: 57.8 (#39), Qwen2-72B: 30.2 (#236)

BenchmarkGrok 4.7Qwen2-72B
LMArena Math14071235
FrontierMath (Tiers 1-3)53%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202598.1%—
ProofBench34%—
MATH Level 5—39.1%

Knowledge Grok 4.7 leads

Grok 4.7: 62.8 (#22), Qwen2-72B: 21.2 (#275)

BenchmarkGrok 4.7Qwen2-72B
GPQA Diamond92.7%40.8%
LMArena Expert14221171
SimpleQA Verified56%—
MMLU—82.4%

Multimodal Not comparable

Grok 4.7: 35.5 (#87), Qwen2-72B: —

BenchmarkGrok 4.7Qwen2-72B
LMArena Vision1228—
Blueprint-Bench 232.5%—
Furniture Assembly20.8%—

Multilingual Grok 4.7 leads

Grok 4.7: 50.8 (#116), Qwen2-72B: 35.9 (#244)

BenchmarkGrok 4.7Qwen2-72B
LMArena Non-English13891176
LMArena Chinese14551240
LMArena French14551170
LMArena Russian13971169
LMArena Spanish14001169
LMArena German—1151
LMArena Japanese—1111
LMArena Korean—1083

Instruction Following Grok 4.7 leads

Grok 4.7: 74.1 (#105), Qwen2-72B: 61.7 (#241)

BenchmarkGrok 4.7Qwen2-72B
LMArena Instruction Following14041181

Long Context Grok 4.7 leads

Grok 4.7: 43.1 (#104), Qwen2-72B: 36.1 (#235)

BenchmarkGrok 4.7Qwen2-72B
LMArena Longer Query14131192

Writing & Preference Grok 4.7 leads

Grok 4.7: 70.0 (#24), Qwen2-72B: 40.8 (#241)

BenchmarkGrok 4.7Qwen2-72B
LMArena Text13991203
LMArena Creative Writing13911181
LMArena Multi-Turn13931196
EQ-Bench Creative Writing2007—

Frequently asked questions

Is Grok 4.7 better than Qwen2-72B?

Grok 4.7 is the stronger model overall, scoring 53.1 to 30.0 on the Noometry Index.

Is Grok 4.7 or Qwen2-72B better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 29.1 in the Noometry coding category.

How many benchmarks do Grok 4.7 and Qwen2-72B share?

16 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper