Noometry

Model comparison

Grok 4.5 vs Qwen2-72B

Grok 4.5 is the stronger model overall, scoring 55.0 to 30.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

Grok 4.5 xAI

55.0

Rank #25 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Grok 4.5 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 4.5 leads 62.3 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 93.4% for Grok 4.5 and 40.8% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Grok 4.5Qwen2-72B
ProviderxAIAlibaba (Qwen)
Noometry Index55.030.0
Released2026-07-082024-06-07
WeightsProprietaryOpen
Context window500K—
Max output500K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked5226

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

Category by category

Coding Grok 4.5 leads

Grok 4.5: 52.2 (#35), Qwen2-72B: 29.1 (#310)

BenchmarkGrok 4.5Qwen2-72B
WeirdML46.4%11.3%
LMArena Coding14741196
DeepSWE53.8%—
FrontierCode42.4%—
LMArena WebDev1553—
SciCode54.1%—
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench1,309—

Agentic & Tool Use Grok 4.5 leads

Grok 4.5: 44.4 (#17), Qwen2-72B: 17.0 (#146)

BenchmarkGrok 4.5Qwen2-72B
APEX-Agents56.2%—
TheAgentCompany—1.1%
τ²-bench Banking47.9%—
PostTrainBench23.4%—
GBAEval65.4%—
GDP.pdf14%—
LMArena Search1213—
METR Time Horizons—29.9%
Vending-Bench 23,887—

Reasoning Grok 4.5 leads

Grok 4.5: 56.1 (#25), Qwen2-72B: 23.2 (#181)

BenchmarkGrok 4.5Qwen2-72B
LMArena Hard Prompts14621191
Epoch Capabilities Index153.92125.28
ARC-AGI-252.6%—
SimpleBench70%—
Kagi LLM Benchmark83.5%—
NYT Connections (extended)79.9%—
ARC-AGI-187.2%—
CritPt15.4%—
Chess Puzzles36%—
DTBench96.5%—
LMCA45.2%—
Surface Evolver Bench74.4%—

Math Grok 4.5 leads

Grok 4.5: 60.9 (#35), Qwen2-72B: 30.2 (#236)

BenchmarkGrok 4.5Qwen2-72B
LMArena Math14591235
FrontierMath (Tiers 1-3)57.2%—
FrontierMath Tier 424.4%—
OTIS Mock AIME 2024-202597.8%—
ProofBench31%—
MATH Level 5—39.1%

Knowledge Grok 4.5 leads

Grok 4.5: 62.3 (#24), Qwen2-72B: 21.2 (#275)

BenchmarkGrok 4.5Qwen2-72B
GPQA Diamond93.4%40.8%
LMArena Expert14661171
SimpleQA Verified48.3%—
MMLU—82.4%

Multimodal Not comparable

Grok 4.5: 37.6 (#72), Qwen2-72B: —

BenchmarkGrok 4.5Qwen2-72B
LMArena Vision1288—
Blueprint-Bench 227.3%—
Furniture Assembly22.5%—
LMArena Document1452—

Multilingual Grok 4.5 leads

Grok 4.5: 54.4 (#42), Qwen2-72B: 35.9 (#244)

BenchmarkGrok 4.5Qwen2-72B
LMArena Non-English14401176
LMArena Chinese14961240
LMArena French14561170
LMArena German14461151
LMArena Japanese14281111
LMArena Korean14041083
LMArena Russian14481169
LMArena Spanish14501169

Instruction Following Grok 4.5 leads

Grok 4.5: 76.0 (#48), Qwen2-72B: 61.7 (#241)

BenchmarkGrok 4.5Qwen2-72B
LMArena Instruction Following14461181

Long Context Grok 4.5 leads

Grok 4.5: 44.8 (#56), Qwen2-72B: 36.1 (#235)

BenchmarkGrok 4.5Qwen2-72B
LMArena Longer Query14631192

Writing & Preference Grok 4.5 leads

Grok 4.5: 65.8 (#42), Qwen2-72B: 40.8 (#241)

BenchmarkGrok 4.5Qwen2-72B
LMArena Text14481203
LMArena Creative Writing14421181
LMArena Multi-Turn14561196
EQ-Bench Creative Writing1579—

Frequently asked questions

Is Grok 4.5 better than Qwen2-72B?

Grok 4.5 is the stronger model overall, scoring 55.0 to 30.0 on the Noometry Index.

Is Grok 4.5 or Qwen2-72B better for coding?

Grok 4.5 scores higher on coding benchmarks: 52.2 versus 29.1 in the Noometry coding category.

How many benchmarks do Grok 4.5 and Qwen2-72B share?

20 benchmarks have published results for both models. Grok 4.5 has 52 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper