Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Qwen1.5-72B

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.5

Rank #48 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.3

Rank #282 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 89.3% for Grok 4.20 (Non-Reasoning) and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Qwen1.5-72B
ProviderxAIAlibaba (Qwen)
Noometry Index48.530.3
Released2026-02-172024-02-04
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked4622

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): 41.8 (#104), Qwen1.5-72B: 31.4 (#272)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Coding14581166
LMArena WebDev1374—
WeirdML52.3%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench1,150—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Grok 4.20 (Non-Reasoning): 34.3 (#43), Qwen1.5-72B: —

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
Terminal-Bench57.3%—
τ²-bench Banking18%—
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.2 (#30), Qwen1.5-72B: 21.2 (#201)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Hard Prompts14511148
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%—
Epoch Capabilities Index152.01—
ForecastBench61.4—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.0 (#54), Qwen1.5-72B: 30.7 (#205)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Math14551164
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202592.2%—
ProofBench14%—

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#54), Qwen1.5-72B: 11.5 (#295)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
GPQA Diamond89.3%28.8%
LMArena Expert14401136
SimpleQA Verified30.2%—

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.2 (#88), Qwen1.5-72B: —

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.7 (#38), Qwen1.5-72B: 33.4 (#248)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Non-English14401135
LMArena Chinese14811186
LMArena French14771158
LMArena German14631084
LMArena Japanese14501061
LMArena Korean14171049
LMArena Russian14571104
LMArena Spanish14421110

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 75.0 (#79), Qwen1.5-72B: 59.6 (#251)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Instruction Following14201142

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.4 (#33), Qwen1.5-72B: 35.0 (#238)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Longer Query14361157
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.9 (#42), Qwen1.5-72B: 37.4 (#253)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen1.5-72B
LMArena Text14511166
LMArena Creative Writing14391137
LMArena Multi-Turn14561160
EQ-Bench Creative Writing1574—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Qwen1.5-72B?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.3 on the Noometry Index.

Is Grok 4.20 (Non-Reasoning) or Qwen1.5-72B better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 31.4 in the Noometry coding category.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen1.5-72B share?

18 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper