Noometry

Model comparison

Grok 4.6 vs Qwen1.5-72B

Grok 4.6 is the stronger model overall, scoring 56.8 to 30.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 4.6 xAI

56.8

Rank #19 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.3

Rank #282 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 4.6 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 4.6 leads 63.3 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 94% for Grok 4.6 and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

Grok 4.6Qwen1.5-72B
ProviderxAIAlibaba (Qwen)
Noometry Index56.830.3
Released2026-08-122024-02-04
WeightsProprietaryOpen
Context window500K—
Max output500K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked4922

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

Category by category

Coding Grok 4.6 leads

Grok 4.6: 58.0 (#14), Qwen1.5-72B: 31.4 (#272)

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Coding14641166
DeepSWE67.5%—
FrontierCode48%—
CursorBench41.4%—
LMArena WebDev1620—
FrontierSWE25.3%—
SciCode56.5%—
WeirdML67.3%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench1,508—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Grok 4.6: 39.4 (#25), Qwen1.5-72B: —

BenchmarkGrok 4.6Qwen1.5-72B
APEX-Agents65.3%—
GDP.pdf17.2%—
Vending-Bench 29,047—

Reasoning Grok 4.6 leads

Grok 4.6: 61.3 (#18), Qwen1.5-72B: 21.2 (#201)

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Hard Prompts14451148
ARC-AGI-267.1%—
SimpleBench75.9%—
NYT Connections (extended)80%—
ARC-AGI-187.5%—
CritPt19.7%—
Chess Puzzles40%—
EBR-Bench30.5%—
Mystery Game Puzzles34%—
DTBench97.3%—
LMCA48.5%—
Epoch Capabilities Index156.48—

Math Grok 4.6 leads

Grok 4.6: 66.8 (#19), Qwen1.5-72B: 30.7 (#205)

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Math14161164
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 431.7%—
OTIS Mock AIME 2024-202599.2%—
ProofBench51%—

Knowledge Grok 4.6 leads

Grok 4.6: 63.3 (#18), Qwen1.5-72B: 11.5 (#295)

BenchmarkGrok 4.6Qwen1.5-72B
GPQA Diamond94%28.8%
LMArena Expert14631136
SimpleQA Verified49.3%—

Multimodal Not comparable

Grok 4.6: 43.9 (#18), Qwen1.5-72B: —

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Vision1265—
Blueprint-Bench 233.2%—
Furniture Assembly40%—
LMArena Document1452—

Multilingual Grok 4.6 leads

Grok 4.6: 53.3 (#67), Qwen1.5-72B: 33.4 (#248)

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Non-English14221135
LMArena Chinese14791186
LMArena French14581158
LMArena German14251084
LMArena Japanese13831061
LMArena Korean13951049
LMArena Russian14271104
LMArena Spanish14081110

Instruction Following Grok 4.6 leads

Grok 4.6: 75.6 (#59), Qwen1.5-72B: 59.6 (#251)

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Instruction Following14311142

Long Context Grok 4.6 leads

Grok 4.6: 44.4 (#62), Qwen1.5-72B: 35.0 (#238)

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Longer Query14531157

Writing & Preference Grok 4.6 leads

Grok 4.6: 62.5 (#77), Qwen1.5-72B: 37.4 (#253)

BenchmarkGrok 4.6Qwen1.5-72B
LMArena Text14271166
LMArena Creative Writing14301137
LMArena Multi-Turn14221160

Frequently asked questions

Is Grok 4.6 better than Qwen1.5-72B?

Grok 4.6 is the stronger model overall, scoring 56.8 to 30.3 on the Noometry Index.

Is Grok 4.6 or Qwen1.5-72B better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.0 versus 31.4 in the Noometry coding category.

How many benchmarks do Grok 4.6 and Qwen1.5-72B share?

18 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper