Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Qwen2-72B

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 30.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) 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 4.20 (Non-Reasoning) leads 52.8 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 89.3% for Grok 4.20 (Non-Reasoning) and 40.8% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Qwen2-72B
ProviderxAIAlibaba (Qwen)
Noometry Index48.630.0
Released2026-02-172024-06-07
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked4626

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), Qwen2-72B: 29.1 (#310)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
WeirdML52.3%11.3%
LMArena Coding14591196
LMArena WebDev1375—
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench1,150—

Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 34.4 (#46), Qwen2-72B: 17.0 (#146)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
Terminal-Bench57.3%—
TheAgentCompany—1.1%
τ²-bench Banking18%—
LMArena Search1189—
METR Time Horizons—29.9%
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Qwen2-72B: 23.2 (#181)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
LMArena Hard Prompts14511191
Epoch Capabilities Index151.98125.28
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
Chess Puzzles24%—
Thematic Generalization63.8%—
DTBench90.1%—
LMCA38.7%—
ForecastBench61.4—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Qwen2-72B: 30.2 (#236)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
LMArena Math14551235
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202592.2%—
ProofBench14%—
MATH Level 5—39.1%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Qwen2-72B: 21.2 (#275)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
GPQA Diamond89.3%40.8%
LMArena Expert14391171
SimpleQA Verified30.2%—
MMLU—82.4%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Qwen2-72B: —

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Qwen2-72B: 35.9 (#244)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
LMArena Non-English14411176
LMArena Chinese14811240
LMArena French14761170
LMArena German14651151
LMArena Japanese14491111
LMArena Korean14171083
LMArena Russian14581169
LMArena Spanish14431169

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Qwen2-72B: 61.7 (#241)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
LMArena Instruction Following14201181

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Qwen2-72B: 36.1 (#235)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
LMArena Longer Query14371192
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Qwen2-72B: 40.8 (#241)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2-72B
LMArena Text14511203
LMArena Creative Writing14381181
LMArena Multi-Turn14561196
EQ-Bench Creative Writing1574—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Qwen2-72B?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 30.0 on the Noometry Index.

Is Grok 4.20 (Non-Reasoning) or Qwen2-72B better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 29.1 in the Noometry coding category.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen2-72B share?

20 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper